Method, apparatus and computer program for power management of energy self-sufficient farm using mushroom medium

Abstract

A method for managing power in an energy-independent farm utilizing a mushroom substrate according to an embodiment of the present invention comprises the steps of: acquiring first data related to a mushroom farm and second data related to the environment of the mushroom farm, wherein the first data includes growth status data of a mushroom being cultivated in the mushroom farm at a first time point, a first power consumption amount indicating the power consumption of the farm at the first time point, and a first power generation amount indicating the power generation amount of the farm at the first time point, and the second data includes first growth environment data indicating the growth environment of the mushroom at the first time point and first weather data indicating the weather conditions of the mushroom farm; and determining the amount of discarded substrate at a second time point by inputting first input data, which includes at least a portion of data obtained by merging the first data and the second data, into a learned first artificial neural network, wherein the second time point is at least one time point after the first time point. The method may include a step of determining a second power consumption amount representing the power consumption of the farm at a third point in time and a second power generation amount representing the power generation amount of the farm at the third point in time by inputting second input data, which includes the amount of discarded medium and at least a portion of the merged data, into a trained second artificial neural network, wherein the third point in time is at least one point in time after the second point in time.

Description

Technology Field

[0001] The present invention relates to a farm management system for an energy-independent farm utilizing a mushroom substrate. Furthermore, the present invention relates to a power management method and a farm management server for an energy-independent farm utilizing a mushroom substrate. Background Technology

[0002] Energy demand has increased due to industrialization, and recently, electricity demand is steadily rising due to the proliferation of various electrical and electronic devices and the introduction of electric vehicles. Traditionally, electricity was primarily obtained from fossil fuels, but there is a trend to reduce their use due to rapidly increasing environmental concerns.

[0003] New and renewable energy sources such as solar, geothermal, wind, and fuel cells are gaining attention as alternatives to conventional fossil fuels. However, solar power generation is limited to locations with high solar radiation and during favorable weather conditions, while fuel cells require a hydrogen supply through water electrolysis; consequently, there is a need for technological development regarding these new energy sources.

[0004] Meanwhile, spent substrate refers to the mushroom growing medium remaining after production, and it is discharged in various forms depending on the raw materials, mixing ratios, and cultivation methods. Furthermore, the types of raw materials and mixing ratios vary depending on the type of mushroom, cultivation method, and the producer, resulting in diverse characteristics of the generated spent substrate.

[0005] Currently, spent substrate is being recycled in various ways, and diverse research is being conducted for its efficient utilization. Specifically, these applications include use as compost in organic and horticultural farming, as substrate for earthworm production, for water quality improvement, as a soil conditioner, and as animal feed.

[0006] Meanwhile, although such waste substrate has high recycling value as fuel, it has so far been utilized only for creating low added value, such as being mixed into fertilizer or compost. The problem to be solved

[0007] The present invention aims to produce energy using by-products of discarded substrates that have expired after being used for mushroom cultivation, and to enable the use of the produced energy for mushroom cultivation.

[0008] In addition, the present invention aims to predict the amount of waste substrate to be generated at a future point in time to improve energy self-sufficiency, and to predict the amount of power generated and the amount of electricity consumed by the farm based on the predicted amount of waste substrate. means of solving the problem

[0009] A farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention may include at least one power generation device for producing power used in the farm, wherein the at least one power generation device comprises a first power generation device that generates energy from by-products of discarded substrates that have expired after being used for mushroom cultivation; a farm management server that generates at least one control signal for controlling the growth environment of the mushrooms, the flow of power within the farm, and the flow of thermal energy within the farm; and an environment creation device that creates the growth environment of the mushrooms.

[0010] The above at least one power generation device may further include a second power generation device that generates power from solar energy; and a third power generation device that receives energy from a power grid.

[0011] The farm management system of an energy-independent farm utilizing the above mushroom substrate may further include: a substrate condition checking device that checks the condition of the substrate used in the mushroom cultivation process and determines at least a portion of the substrate as the discarded substrate; and a substrate processing device that processes the discarded substrate into a form usable for power production in the first power production device.

[0012] The above-described medium processing device generates pellets from the waste medium according to at least one processing process, and the pellets are used as raw materials for power generation in the first power generation device, and the at least one processing process may include a torrefaction process of the waste medium.

[0013] The above-described environment creation device may include: a pellet boiler that generates warmth supplied to the farm by the combustion of pellets generated from the waste medium; and a heat pump that generates either warmth or cold air supplied to the farm using power supplied from at least one power generation device.

[0014] The farm management system of an energy-independent farm utilizing the above mushroom substrate further includes: a first monitoring device for monitoring the growth environment of the farm; and a second monitoring device for monitoring the growth environment of a secondary crop cultivated using by-products generated from the cultivation of the mushrooms; wherein the monitoring data of each of the first monitoring device and the second monitoring device is transmitted to the farm management server, and the farm management server can generate the at least one control signal based on the monitoring data.

[0015] The farm management server receives the respective power production amount from the at least one power generation device, receives the growth environment from at least one monitoring device that monitors the growth environment of the farm, receives the power consumption of the environment creation device, and can determine the target growth environment of the farm based on the received data.

[0016] A method for managing power in an energy-independent farm utilizing a mushroom substrate according to an embodiment of the present invention comprises the steps of: acquiring first data related to a mushroom farm and second data related to the environment of the mushroom farm, wherein the first data includes growth status data of a mushroom being cultivated in the mushroom farm at a first time point, a first power consumption amount indicating the power consumption of the farm at the first time point, and a first power generation amount indicating the power generation amount of the farm at the first time point, and the second data includes first growth environment data indicating the growth environment of the mushroom at the first time point and first weather data indicating the weather conditions of the mushroom farm; and determining the amount of discarded substrate at a second time point by inputting first input data, which includes at least a portion of data obtained by merging the first data and the second data, into a learned first artificial neural network, wherein the second time point is at least one time point after the first time point. The method may include a step of determining a second power consumption amount representing the power consumption of the farm at a third point in time and a second power generation amount representing the power generation amount of the farm at the third point in time by inputting second input data, which includes the amount of discarded medium and at least a portion of the merged data, into a trained second artificial neural network, wherein the third point in time is at least one point in time after the second point in time.

[0017] The first input data above may include growth status data at the first time point, the first growth environment data, and the first weather data.

[0018] The second input data above may include the amount of the discarded badge, the first power consumption, the first power generation amount, and the first weather data.

[0019] The power management method for an energy-independent farm utilizing the above mushroom substrate may further include, after the step of determining the second power consumption and the second power generation amount, the step of calculating the surplus power amount of the mushroom farm at the third point in time based on the second power consumption and the second power generation amount; and the step of determining the power amount to be converted into thermal energy among the surplus power. At this time, the power corresponding to the power amount to be converted may be converted into thermal energy stored in a space corresponding to the mushroom farm through a heat pump provided in the mushroom farm.

[0020] A power management method for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention may further include a step of training each of the first artificial neural network and the second artificial neural network prior to the step of acquiring the first data and the second data.

[0021] The above training step includes the step of training the first artificial neural network using first training data; wherein the first training data includes mushroom growth data at a fourth time point, growth environment data at the fourth time point, and weather data at the fourth time point as first training input data, and includes the amount of discarded substrate at a fifth time point after the fourth time point as first training output data, and the first artificial neural network may be a neural network trained to output the first training output data according to the input of the first training input data.

[0022] The above training step includes the step of training the second artificial neural network using second training data; wherein the second training data includes the amount of discarded badges at a fifth time point, the amount of power consumption at a fourth time point prior to the fifth time point, the amount of power generated at the fourth time point, and the weather data at the fourth time point as second training input data, and includes the amount of power consumption at a sixth time point and the amount of power generated at the sixth time point as second training output data, and the sixth time point is a time point after the fifth time point; and the second artificial neural network may be a neural network trained to output the second training output data according to the input of the second training input data.

[0023] The above second power generation amount may be an amount determined based on the sum of the second-1 power generation amount based on pellets generated from waste media and the second-2 power generation amount based on solar energy.

[0024] A farm management server for an energy-independent farm utilizing a mushroom substrate according to an embodiment of the present invention acquires first data related to a mushroom farm and second data related to the environment of the mushroom farm, wherein the first data includes growth status data of a mushroom being cultivated in the mushroom farm at a first time point, a first power consumption amount indicating the power consumption of the farm at the first time point, and a first power generation amount indicating the power generation amount of the farm at the first time point, and the second data includes first growth environment data indicating the growth environment of the mushroom at the first time point and first weather data indicating the weather conditions of the mushroom farm, and inputs first input data including at least a portion of data obtained by merging the first data and the second data into a trained first artificial neural network to determine the amount of discarded substrate at a second time point, wherein the second time point is at least one time point after the first time point, and inputs second input data including the amount of discarded substrate and at least a portion of the merged data into a trained second artificial neural network to determine a second power consumption amount indicating the power consumption of the farm at a third time point and a second power generation amount indicating the power generation amount of the farm at the third time point. The amount of power generated is determined, and the third point in time may be at least one point in time after the second point in time.

[0025] The first input data above may include growth status data at the first time point, the first growth environment data, and the first weather data.

[0026] The second input data above may include the amount of the discarded badge, the first power consumption, the first power generation amount, and the first weather data.

[0027] The farm management server calculates the surplus power of the mushroom farm at the third point in time based on the second power consumption and the second power generation, determines the amount of power to be converted into thermal energy among the surplus power, and the power corresponding to the amount of power to be converted can be converted into thermal energy stored in a space corresponding to the mushroom farm through a heat pump provided in the mushroom farm.

[0028] The above farm management server can train each of the above first artificial neural network and the above second artificial neural network.

[0029] The farm management server above trains the first artificial neural network using first training data, wherein the first training data includes mushroom growth data at a fourth time point, growth environment data at the fourth time point, and weather data at the fourth time point as first training input data, and includes the amount of discarded substrate at a fifth time point after the fourth time point as first training output data, and the first artificial neural network may be a neural network trained to output the first training output data according to the input of the first training input data.

[0030] The farm management server above trains the second artificial neural network using second training data, wherein the second training data includes the amount of discarded substrate at the fifth time point, the amount of power consumption at the fourth time point prior to the fifth time point, the amount of power generated at the fourth time point, and the weather data at the fourth time point as second training input data, and includes the amount of power consumption at the sixth time point and the amount of power generated at the sixth time point as second training output data, wherein the sixth time point is a time point after the fifth time point, and the second artificial neural network may be a neural network trained to output the second training output data according to the input of the second training input data.

[0031] The above second power generation amount may be an amount determined based on the sum of the second-1 power generation amount based on pellets generated from waste media and the second-2 power generation amount based on solar energy. Effects of the invention

[0032] According to the present invention, energy can be produced using by-products of discarded substrates that have expired after being used for mushroom cultivation, and the produced energy can be used for mushroom cultivation.

[0033] In addition, to improve energy self-sufficiency, the amount of waste substrate to be generated at a future point in time can be predicted, and based on the predicted amount of waste substrate, the farm's power generation and electricity consumption can be predicted. Brief explanation of the drawing

[0034] FIG. 1 is a schematic diagram illustrating the configuration of a farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention. FIG. 2 is a schematic diagram illustrating the configuration of a farm management server (100) according to one embodiment of the present invention. FIG. 3 is a schematic diagram illustrating the configuration of a user terminal (200) according to one embodiment of the present invention. FIG. 4 is a diagram illustrating an exemplary structure of an artificial neural network learned by a farm management server (100) according to one embodiment of the present invention. FIG. 5 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention learning a first artificial neural network (720) using first learning data (710). FIG. 6 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned first artificial neural network (720). FIG. 7 is a diagram illustrating the process of a farm management server (100) according to an embodiment of the present invention learning a second artificial neural network (820) using second learning data (810). FIG. 8 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned second artificial neural network (820). FIG. 9 is a diagram illustrating the process of a farm management server (100) managing power at a farm according to one embodiment of the present invention. FIG. 10 is a flowchart illustrating a method for managing power in an energy-independent farm using a mushroom substrate, performed by a farm management server (100) according to one embodiment of the present invention. Specific details for implementing the invention

[0035] The present invention is capable of various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described below in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms.

[0036] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0037] In the following embodiments, terms such as "first," "second," etc., are used not in a limiting sense, but for the purpose of distinguishing one component from another. In the following embodiments, singular expressions include plural expressions unless the context clearly indicates otherwise. In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification exist, and do not preclude the possibility that one or more other features or components may be added. In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and shape of each component shown in the drawings were depicted arbitrarily for convenience of explanation, and therefore the present invention is not necessarily limited to what is depicted.

[0039] FIG. 1 is a schematic diagram illustrating the configuration of a farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention.

[0040] A farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention produces energy by utilizing by-products of discarded substrates that have expired after being used for mushroom cultivation, and can use the produced energy for mushroom cultivation.

[0041] As shown in FIG. 1, a farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention may include a farm management server (100), a user terminal (200), a power generation device (300), an environment creation device (400), a substrate processing device (510), and a monitoring device (600).

[0043] A farm management server (100) according to one embodiment of the present invention can generate at least one control signal that controls the growth environment of mushrooms in the farm, the flow of electricity in the farm, and the flow of thermal energy in the farm.

[0044] In addition, a farm management server (100) according to one embodiment of the present invention may predict the amount of waste medium to be generated at a future point in time and predict the amount of power generated by the farm and the amount of power consumed by the farm based on the predicted amount of waste medium.

[0045] In addition, a farm management server (100) according to one embodiment of the present invention may receive power production from a power generation device (300), receive a growth environment from a monitoring device (600) that monitors the growth environment of the farm, receive power consumption from an environment creation device (400), and determine a target growth environment of the farm based on the received data.

[0047] FIG. 2 is a schematic diagram illustrating the configuration of a farm management server (100) according to an embodiment of the present invention. Referring to FIG. 2, the farm management server (100) according to an embodiment of the present invention may include a communication unit (110), a first processor (120), a memory (130), and a second processor (140). Additionally, although not illustrated in the drawing, the farm management server (100) according to an embodiment of the present invention may further include an input / output unit, a program storage unit, etc.

[0048] The communication unit (110) may be a device including hardware and software necessary for the farm management server (100) to transmit and receive signals, such as control signals or data signals, through a wired or wireless connection with another network device, such as a user terminal (200).

[0049] The first processor (120) can control a series of processes that generate at least one control signal to regulate the growth environment of mushrooms, the flow of electricity within the farm, and the flow of thermal energy within the farm. Additionally, the first processor (120) may be a device that controls a series of processes that predict the amount of waste substrate to be generated at a future point in time, and predict the amount of power generated and the amount of electricity consumed by the farm based on the predicted amount of waste substrate.

[0050] In this case, a processor may refer to a data processing device embedded in hardware that has a physically structured circuit to perform functions expressed by code or instructions included in a program, for example. Examples of such data processing devices embedded in hardware may include microprocessors, central processing units (CPUs), processor cores, multiprocessors, application-specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs), but the scope of the present invention is not limited thereto.

[0051] The memory (130) performs the function of temporarily or permanently storing data processed by the farm management server (100). The memory may include magnetic storage media or flash storage media, but the scope of the invention is not limited thereto.

[0052] The second processor (140) may refer to a device that performs calculations under the control of the first processor (120) described above. In this case, the second processor (140) may be a device having a higher computational capability than the first processor (120) described above. For example, the second processor (140) may be composed of a GPU (Graphics Processing Unit).

[0053] In one embodiment of the present invention, the second processor (140) may be used in the learning process of an artificial neural network or in the computation process using the learned artificial neural network. A detailed description of the data processing process using the artificial neural network will be provided later. In one embodiment of the present invention, the second processor (140) may be a plurality or a singular number.

[0055] A user terminal (200) according to one embodiment of the present invention can provide content related to the status of a farm provided by a farm management server (100) to the user, and receive input from the user and transmit it to the farm management server (100).

[0056] FIG. 3 is a schematic diagram illustrating the configuration of a user terminal (200) according to an embodiment of the present invention. Referring to FIG. 3, a user terminal (200) according to an embodiment of the present invention may include a communication unit (210), a third processor (220), a memory (230), and an input / output interface (240).

[0057] The communication unit (210) may be a device including hardware and software necessary for the user terminal (200) to transmit and receive signals, such as control signals or data signals, through a wired or wireless connection with another network device, such as a farm management server (100).

[0058] The third processor (220) can provide content related to the status of the farm provided by the farm management server (100) to the user, receive the user's request, and transmit it to the farm management server (100).

[0059] In this case, a processor may refer to a data processing device embedded in hardware that has a physically structured circuit to perform functions expressed by code or instructions included in a program, for example. Examples of such data processing devices embedded in hardware may include microprocessors, central processing units (CPUs), processor cores, multiprocessors, application-specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs), but the scope of the present invention is not limited thereto.

[0060] The memory (230) performs the function of temporarily or permanently storing data processed by the user terminal (200). The memory may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto.

[0061] The input / output interface (240) may be a means for interfacing with an input / output device (not shown) that obtains user input. In this case, the input device may include, for example, a device such as a keyboard or a mouse, and the output device may include a device such as a display.

[0062] A user terminal (200) according to one embodiment of the present invention may mean a portable electronic device (201, 202, 203) or a computer (204). In this specification, the user terminal (200) may sometimes be described as a 'computing device'.

[0064] A power generation device (300) according to one embodiment of the present invention is a device that produces or receives power used for cultivating mushrooms in a farm, and may be one or more.

[0065] For example, the power generation device (300) may include a first power generation device (310) that generates energy from by-products of discarded substrate that has expired after being used for mushroom cultivation.

[0066] Additionally, the power generation device (300) may include a second power generation device (320) that generates power from solar energy and a third power generation device (330) that receives energy from a power grid.

[0067] However, the configuration of such a power generation device (300) is exemplary and the concept of the present invention is not limited thereto.

[0068] Meanwhile, the first power generation device (310) described above may be a device that generates electricity using pellets produced from waste substrate as fuel. For example, the first power generation device (310) may be a biomass-type power generation device that generates electricity from thermal energy generated when pellets are burned. However, this is merely an example and the concept of the present invention is not limited thereto, and various types of power generation devices using waste substrate may correspond to the first power generation device (310).

[0070] An environment creation device (400) according to one embodiment of the present invention may refer to various types of devices for creating a growth environment for mushrooms within a farm.

[0071] For example, the environment creation device (400) may include a heat pump (410) that generates either warm air or cold air supplied to the farm using power supplied from the power generation device (300).

[0072] Additionally, the environment creation device (400) may include a pellet boiler (420) that generates warmth supplied to the farm through the combustion of pellets produced from waste media.

[0073] However, the configuration of such an environment creation device (400) is exemplary and the concept of the present invention is not limited thereto.

[0074] Meanwhile, the heat pump (410) described above can store surplus electricity produced by the power generation device (300) in the form of thermal energy in the farm.

[0076] Although not illustrated in FIG. 1, a farm management system for an energy-independent farm utilizing a mushroom substrate according to one embodiment of the present invention may further include a substrate condition checking device (not illustrated) that checks the condition of the substrate used in the mushroom cultivation process and determines at least a portion of the substrate as a discarded substrate.

[0077] For example, a medium condition checking device (not shown) may determine whether a medium is a discarded medium based on an image of the medium in use or based on at least one parameter related to the medium in use (weight, humidity, expiration date, etc.). However, this is exemplary and the scope of the present invention is not limited thereto.

[0079] A culture medium processing device (510) according to one embodiment of the present invention may be a device that processes a culture medium identified as a discarded culture medium by a culture medium status checking device (not shown) into a form usable for power production in a first power generation device (310).

[0080] For example, the medium processing device (510) may be a device that generates pellets from waste medium according to at least one processing process. At this time, the pellets generated by the medium processing device (510) may be used as raw materials for power generation in the first power generation device (310). In addition, at least one processing process performed by the medium processing device (510) may include a torrefaction process of the waste medium.

[0082] A monitoring device (600) according to one embodiment of the present invention may be a device for monitoring the growth environment of a farm where mushrooms are grown or for monitoring the growth environment of a secondary crop.

[0083] For example, the monitoring device (600) may include a first monitoring device (610) that monitors the growth environment of a farm where mushrooms are grown.

[0084] Additionally, the monitoring device (600) may include a second monitoring device (620) for monitoring the growth environment of a secondary crop cultivated using by-products generated from the cultivation of mushrooms at a mushroom farm. In this case, the by-products may include carbon dioxide.

[0085] Meanwhile, monitoring data from each of the first monitoring device (610) and the second monitoring device (620) is transmitted to the farm management server (100), and the farm management server (100) can generate at least one control signal based on the monitoring data.

[0087] A communication network (Net) according to one embodiment of the present invention may refer to a path that mediates data transmission and reception between each component of a system. For example, the communication network (Net) may include wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), and ISDNs (Integrated Service Digital Networks), or wireless networks such as wireless LANs, CDMA, Bluetooth, and satellite communication, but the scope of the present invention is not limited thereto.

[0088] The following describes the power management process performed by the farm management server (100).

[0090] FIG. 4 is a diagram illustrating an exemplary structure of an artificial neural network learned by a farm management server (100) according to one embodiment of the present invention.

[0091] An artificial neural network according to one embodiment of the present invention may be an artificial neural network based on a Recurrent Neural Network (RNN) model as illustrated in FIG. 4.

[0092] Referring to FIG. 4, an artificial neural network according to such a recurrent neural network (RNN) model may include an input layer (L1) including at least one input node (N1), a hidden layer (L2) including a plurality of hidden nodes (N2), and an output layer (L3) including at least one output node (N3).

[0093] The hidden layer (L2) may include one or more fully connected layers as illustrated. If the hidden layer (L2) includes multiple layers, the artificial neural network may include a function (not illustrated) that defines the relationship between each hidden layer.

[0094] At least one output node (N3) of the output layer (L3) may include an output value generated by an artificial neural network from an input value of the input layer (L1) under the control of the first processor (120).

[0095] Meanwhile, the values ​​included in each node of each layer can be vectors. Additionally, each node may include a weight corresponding to the importance of that node.

[0096] Meanwhile, the artificial neural network may include a first function (F1) that defines the relationship between the input layer (L1) and the hidden layer (L2), and a second function (F2) that defines the relationship between the hidden layer (L2) and the output layer (L3).

[0097] The first function (F1) can define the connection between an input node (N1) included in the input layer (L1) and a hidden node (N2) included in the hidden layer (L2). Similarly, the second function (F2) can define the connection between a hidden node (N2) included in the hidden layer (L2) and an output node (N3) included in the output layer (L3).

[0098] The functions between the first function (F1), the second function (F2), and the hidden layer may include a recurrent neural network model that outputs a result based on the input of the previous node.

[0099] In the process of training an artificial neural network by the first processor (120), a first function (F1) and a second function (F2) can be trained based on multiple training data. Of course, in the process of training the artificial neural network, functions between multiple hidden layers can also be trained in addition to the aforementioned first function (F1) and second function (F2).

[0100] An artificial neural network according to one embodiment of the present invention can be trained using a supervised learning method based on labeled training data.

[0101] A first processor (120) according to one embodiment of the present invention can train an artificial neural network by repeatedly performing a process of updating the aforementioned functions (F1, F2, functions between hidden layers, etc.) such that an output value generated by inputting one of the input data into the artificial neural network using a plurality of training data is close to a value labeled in the training data.

[0102] At this time, the first processor (120) according to one embodiment of the present invention may update the aforementioned functions (F1, F2, functions between hidden layers, etc.) according to a back propagation algorithm. However, this is exemplary and the concept of the present invention is not limited thereto.

[0103] The types and / or structures of artificial neural networks described in FIG. 4 are exemplary and the scope of the invention is not limited thereto. Accordingly, various types of artificial neural network models may correspond to the 'artificial neural network' described in the specification.

[0104] Below, the process of a farm management server (100) training an artificial neural network is explained first, and the process of predicting power consumption and power generation using the trained artificial neural network is explained later.

[0106] The learning process of artificial neural networks

[0107] In the present invention, the term 'artificial neural network' may be used as a concept encompassing a first artificial neural network and a second artificial neural network. In this case, the 'first artificial neural network' may be a neural network trained to output the amount of discarded substrate at a second time point after the first time point, upon inputting mushroom growth data at a first time point, growth environment data at a first time point, and weather data at a first time point.

[0108] Meanwhile, the 'second artificial neural network' may be a neural network trained to output power consumption and power generation at a third time point after the second time point, upon inputting the amount of discarded badges at the second time point, power consumption at the first time point, power generation at the first time point, and weather data at the first time point.

[0109] Such first artificial neural networks and second artificial neural networks can be trained using a supervised learning method based on multiple training data.

[0111] FIG. 5 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention learning a first artificial neural network (720) using first learning data (710).

[0112] A first artificial neural network according to one embodiment of the present invention may mean a neural network that learns (or learns) the correlation between mushroom growth data at a first time point, growth environment data at a first time point, weather data at a first time point, and the amount of discarded substrate at a second time point after the first time point.

[0113] At this time, the individual learning data constituting the first learning data (710) may include mushroom growth data at the fourth time point, growth environment data at the fourth time point, and weather data at the fourth time point as the first learning input data, and may include the amount of discarded substrate at the fifth time point after the fourth time point as the first learning output data.

[0114] For example, the first learning data (711) may include mushroom growth data (711A), growth environment data (711B), and weather data (711C) at the fourth time point as the first learning input data, and the amount of discarded substrate (711D) at the fifth time point after the fourth time point may be included as the first learning output data. Similarly, the second learning data (712) and the third learning data (713) may each include the items described above.

[0115] A farm management server (100) according to one embodiment of the present invention may train a first artificial neural network (720) using a first processor (120) and / or a second processor (140). For example, the farm management server (100) may input mushroom growth data (711A), growth environment data (711B), and weather data (711C) at a fourth time point to the first artificial neural network (720), and update at least one coefficient and / or weight constituting the artificial neural network (720) so that the amount of discarded substrate output at that time approaches the amount of discarded substrate (711D) at a fifth time point. The farm management server (100) may perform training in a direction that reduces the error rate by using multiple training data or by repeating the above-described process using the same training data.

[0117] FIG. 6 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned first artificial neural network (720).

[0118] A first artificial neural network (720) according to one embodiment of the present invention can be trained to output the amount of discarded substrate at a fifth time point after the fourth time point, based on the first training data (710) described above, as mushroom growth data at a fourth time point, growth environment data at a fourth time point, and weather data at a fourth time point are input. In other words, the first artificial neural network (720) may be a neural network that has learned (or learns) the correlation between mushroom growth data at a fourth time point, growth environment data at a fourth time point, weather data at a fourth time point, and the amount of discarded substrate at a fifth time point after the fourth time point.

[0119] Accordingly, the first artificial neural network (720) according to one embodiment of the present invention can output the amount (722) of discarded substrate at a second time point after the first time point as input data (721) including growth data of mushrooms at a first time point, growth environment data at a first time point, and weather data at a first time point is input.

[0120] Accordingly, a farm management server (100) according to one embodiment of the present invention inputs input data (721) based on a first time point (T1) and can obtain the amount of discarded substrate relating to a second time point (T2) as the output. The obtained amount of discarded substrate can be used to determine the expected power generation amount and the expected power consumption amount in the process described below, and a detailed explanation thereof will be provided later.

[0122] FIG. 7 is a diagram illustrating the process of a farm management server (100) according to an embodiment of the present invention learning a second artificial neural network (820) using second learning data (810).

[0123] A second artificial neural network (820) according to one embodiment of the present invention may mean a neural network that learns (or learns) the correlation between the amount of discarded badges at a second time point, the amount of power consumption at a first time point prior to the second time point, the amount of power generated at a first time point and the weather data at a first time point, the amount of power consumed at a third time point after the second time point and the amount of power generated at a third time point.

[0124] At this time, the individual learning data constituting the second learning data (810) may include the amount of discarded badges at the fifth time point, the amount of power consumption at the fourth time point prior to the fifth time point, the amount of power generated at the fourth time point, and the weather data at the fourth time point as second learning input data, and may include the amount of power consumption at the sixth time point and the amount of power generated at the sixth time point as second learning output data. At this time, the sixth time point may be a time point after the fifth time point.

[0125] For example, the first learning data (811) may include the amount of discarded badges at the fifth time point (811A), the amount of power consumption at the fourth time point prior to the fifth time point (811B), the amount of power generated at the fourth time point (811C), and the weather data at the fourth time point (811D) as second learning input data, and the amount of power consumption at the sixth time point (811E) and the amount of power generated at the sixth time point (811F) as second learning output data. Similarly, the second learning data (812) and the third learning data (813) may each include the items described above.

[0126] A farm management server (100) according to one embodiment of the present invention may train a second artificial neural network (820) using a first processor (120) and / or a second processor (140). For example, the farm management server (100) may input second training input data to the second artificial neural network (820), including the amount of discarded growing medium at a fifth time point (811A), the amount of power consumption at a fourth time point prior to the fifth time point (811B), the amount of power generated at a fourth time point (811C), and the weather data at a fourth time point (811D). Then, at least one coefficient and / or weight constituting the artificial neural network (820) may be updated so that the output amount of power consumption and power generated at that time approaches the amount of power consumption (811E) and the amount of power generated at a sixth time point (811F). The farm management server (100) may perform training in a direction that reduces the error rate by using multiple training data or by repeating the above-described process using the same training data.

[0127] Meanwhile, the amount of power generated at the 4th time point (811C) and the amount of power generated at the 6th time point (811F) described above may each be an amount determined based on the sum of the 2-1 amount of power generated based on pellets produced from waste media at each time point and the 2-2 amount of power generated based on solar energy.

[0129] FIG. 8 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned second artificial neural network (820).

[0130] A second artificial neural network (820) according to one embodiment of the present invention can be trained to output power consumption and power generation at a sixth time point based on the second training data (810) described above, as input the amount of discarded badges at a fifth time point, power consumption at a fourth time point prior to the fifth time point, power generation at a fourth time point, and weather data at a fourth time point. At this time, the sixth time point may be a time point after the fifth time point.

[0131] In other words, the second artificial neural network (820) may be a neural network that has learned (or is learning) the correlation between the amount of discarded badges at the second time point, the amount of power consumption at the first time point prior to the second time point, the amount of power generated at the first time point and the weather data at the first time point, the amount of power consumption at the third time point after the second time point and the amount of power generated at the third time point.

[0132] Accordingly, the second artificial neural network (820) according to one embodiment of the present invention can output output data (822) including power consumption at a third time point after the second time point and power generation at a third time point, as input data (821) including the amount of discarded badges at a second time point, power consumption at a first time point prior to the second time point, power generation at a first time point, and weather data at a first time point is input.

[0133] Accordingly, a farm management server (100) according to one embodiment of the present invention inputs input data (821) based on a first time point (T1) and a second time point (T2), and can obtain power consumption and power generation amounts related to a third time point (T2) as outputs.

[0134] The following description is based on the premise that the first artificial neural network (720) and the second artificial neural network (820) have been trained according to the process described in FIGS. 8.

[0136] Power management method for energy-independent farms using mushroom substrate

[0137] A farm management server (100) according to one embodiment of the present invention can predict the amount of waste medium to be generated at a future point in time and predict the amount of power generated by the farm and the amount of power consumed by the farm based on the predicted amount of waste medium.

[0138] FIG. 9 is a diagram illustrating the process of a farm management server (100) managing power at a farm according to one embodiment of the present invention.

[0139] A farm management server (100) according to one embodiment of the present invention can obtain first data related to a mushroom farm and second data related to the environment of the mushroom farm.

[0140] At this time, the first data may include, for example, growth status data (Growth_T1) of a mushroom being cultivated at the mushroom farm at a first time point (T1), a first power consumption amount (Power_Con_T1) representing the power consumption of the farm at the first time point (T1), and a first power generation amount (Power_Gen_T1) representing the power generation amount of the farm at the first time point (T1).

[0141] Additionally, the second data may include, for example, first growth environment data (Growth_enviro_T1) representing the growth environment of the mushroom at the first time point (T1) and first weather data (Weather_T1) representing the weather conditions of the mushroom farm.

[0142] A farm management server (100) according to one embodiment of the present invention can generate data by merging the first data and the second data described above. For example, the farm management server (100) can generate merged data that includes all items of the first data and all items of the second data.

[0143] A farm management server (100) according to one embodiment of the present invention can determine the amount of discarded medium (Medium_WT_T2) at a second time point (T2) by inputting first input data, which includes at least a portion of the merged data described above, into a trained first artificial neural network (720). At this time, the first input data may include growth status data (Growth_T1), first growth environment data (Growth_enviro_T1), and first weather data (Weather_T1) at a first time point (T1). However, the configuration of such first input data is exemplary and the concept of the present invention is not limited thereto.

[0145] A farm management server (100) according to one embodiment of the present invention can determine a second power consumption amount (Power_Con_T3) representing the power consumption amount of the farm at the third time point (T3) and a second power generation amount (Power_Gen_T3) representing the power generation amount of the farm at the third time point (T3) by inputting second input data, which includes at least a portion of the amount of discarded medium (Medium_WT_T2) generated by the first artificial neural network (720), into a trained second artificial neural network (820). At this time, the second input data may include a first power consumption amount (Power_Con_T1), a first power generation amount (Power_Gen_T1), and first weather data (Weather_T1) in addition to the aforementioned amount of discarded medium (Medium_WT_T2).

[0146] Thus, the present invention can predict power generation and power consumption based on the amount of waste media to be generated at a future point in time.

[0148] A farm management server (100) according to one embodiment of the present invention can calculate the surplus power of a mushroom farm at a third time point (T3) based on the second power consumption (Power_Con_T3) and the second power generation (Power_Gen_T3) calculated according to the process described above. For example, the farm management server (100) can calculate the surplus power of a mushroom farm based on the difference between the second power generation (Power_Gen_T3) and the second power consumption (Power_Con_T3).

[0149] A farm management server (100) according to one embodiment of the present invention can determine the amount of power to be converted into thermal energy among the calculated surplus power. At this time, the power corresponding to the amount of power to be converted can be converted into thermal energy stored in a space corresponding to the mushroom farm through a heat pump (410) provided in the mushroom farm.

[0150] In this way, when the amount of power generated is greater than the amount of electricity consumed, the surplus energy can be converted into thermal energy and stored in the space of the farm.

[0152] FIG. 10 is a flowchart illustrating a method for managing power in an energy-independent farm utilizing a mushroom substrate, performed by a farm management server (100) according to an embodiment of the present invention. The following description refers once again to FIGS. 5 through 9.

[0153] A farm management server (100) according to one embodiment of the present invention can train a first artificial neural network and a second artificial neural network. (S1010)

[0154] In the present invention, the term 'artificial neural network' may be used as a concept encompassing a first artificial neural network and a second artificial neural network. In this case, the 'first artificial neural network' may be a neural network trained to output the amount of discarded substrate at a second time point after the first time point, upon inputting mushroom growth data at a first time point, growth environment data at a first time point, and weather data at a first time point.

[0155] Meanwhile, the 'second artificial neural network' may be a neural network trained to output power consumption and power generation at a third time point after the second time point, upon inputting the amount of discarded badges at the second time point, power consumption at the first time point, power generation at the first time point, and weather data at the first time point.

[0156] Such first artificial neural networks and second artificial neural networks can be trained using a supervised learning method based on multiple training data.

[0158] FIG. 5 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention learning a first artificial neural network (720) using first learning data (710).

[0159] A first artificial neural network according to one embodiment of the present invention may mean a neural network that learns (or learns) the correlation between mushroom growth data at a first time point, growth environment data at a first time point, weather data at a first time point, and the amount of discarded substrate at a second time point after the first time point.

[0160] At this time, the individual learning data constituting the first learning data (710) may include mushroom growth data at the fourth time point, growth environment data at the fourth time point, and weather data at the fourth time point as the first learning input data, and may include the amount of discarded substrate at the fifth time point after the fourth time point as the first learning output data.

[0161] For example, the first learning data (711) may include mushroom growth data (711A), growth environment data (711B), and weather data (711C) at the fourth time point as the first learning input data, and the amount of discarded substrate (711D) at the fifth time point after the fourth time point may be included as the first learning output data. Similarly, the second learning data (712) and the third learning data (713) may each include the items described above.

[0162] A farm management server (100) according to one embodiment of the present invention may train a first artificial neural network (720) using a first processor (120) and / or a second processor (140). For example, the farm management server (100) may input mushroom growth data (711A), growth environment data (711B), and weather data (711C) at a fourth time point to the first artificial neural network (720), and update at least one coefficient and / or weight constituting the artificial neural network (720) so that the amount of discarded substrate output at that time approaches the amount of discarded substrate (711D) at a fifth time point. The farm management server (100) may perform training in a direction that reduces the error rate by using multiple training data or by repeating the above-described process using the same training data.

[0164] FIG. 6 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned first artificial neural network (720).

[0165] A first artificial neural network (720) according to one embodiment of the present invention can be trained to output the amount of discarded substrate at a fifth time point after the fourth time point, based on the first training data (710) described above, as mushroom growth data at a fourth time point, growth environment data at a fourth time point, and weather data at a fourth time point are input. In other words, the first artificial neural network (720) may be a neural network that has learned (or learns) the correlation between mushroom growth data at a fourth time point, growth environment data at a fourth time point, weather data at a fourth time point, and the amount of discarded substrate at a fifth time point after the fourth time point.

[0166] Accordingly, the first artificial neural network (720) according to one embodiment of the present invention can output the amount (722) of discarded substrate at a second time point after the first time point as input data (721) including growth data of mushrooms at a first time point, growth environment data at a first time point, and weather data at a first time point is input.

[0167] Accordingly, a farm management server (100) according to one embodiment of the present invention inputs input data (721) based on a first time point (T1) and can obtain the amount of discarded substrate relating to a second time point (T2) as the output. The obtained amount of discarded substrate can be used to determine the expected power generation amount and the expected power consumption amount in the process described below, and a detailed explanation thereof will be provided later.

[0169] FIG. 7 is a diagram illustrating the process of a farm management server (100) according to an embodiment of the present invention learning a second artificial neural network (820) using second learning data (810).

[0170] A second artificial neural network (820) according to one embodiment of the present invention may mean a neural network that learns (or learns) the correlation between the amount of discarded badges at a second time point, the amount of power consumption at a first time point prior to the second time point, the amount of power generated at a first time point and the weather data at a first time point, the amount of power consumed at a third time point after the second time point and the amount of power generated at a third time point.

[0171] At this time, the individual learning data constituting the second learning data (810) may include the amount of discarded badges at the fifth time point, the amount of power consumption at the fourth time point prior to the fifth time point, the amount of power generated at the fourth time point, and the weather data at the fourth time point as second learning input data, and may include the amount of power consumption at the sixth time point and the amount of power generated at the sixth time point as second learning output data. At this time, the sixth time point may be a time point after the fifth time point.

[0172] For example, the first learning data (811) may include the amount of discarded badges at the fifth time point (811A), the amount of power consumption at the fourth time point prior to the fifth time point (811B), the amount of power generated at the fourth time point (811C), and the weather data at the fourth time point (811D) as second learning input data, and the amount of power consumption at the sixth time point (811E) and the amount of power generated at the sixth time point (811F) as second learning output data. Similarly, the second learning data (812) and the third learning data (813) may each include the items described above.

[0173] A farm management server (100) according to one embodiment of the present invention may train a second artificial neural network (820) using a first processor (120) and / or a second processor (140). For example, the farm management server (100) may input second training input data to the second artificial neural network (820), including the amount of discarded growing medium at a fifth time point (811A), the amount of power consumption at a fourth time point prior to the fifth time point (811B), the amount of power generated at a fourth time point (811C), and the weather data at a fourth time point (811D). Then, at least one coefficient and / or weight constituting the artificial neural network (820) may be updated so that the output amount of power consumption and power generated at that time approaches the amount of power consumption (811E) and the amount of power generated at a sixth time point (811F). The farm management server (100) may perform training in a direction that reduces the error rate by using multiple training data or by repeating the above-described process using the same training data.

[0174] Meanwhile, the amount of power generated at the 4th time point (811C) and the amount of power generated at the 6th time point (811F) described above may each be an amount determined based on the sum of the 2-1 amount of power generated based on pellets produced from waste media at each time point and the 2-2 amount of power generated based on solar energy.

[0176] FIG. 8 is a diagram illustrating the process of a farm management server (100) according to one embodiment of the present invention generating output data using a learned second artificial neural network (820).

[0177] A second artificial neural network (820) according to one embodiment of the present invention can be trained to output power consumption and power generation at a sixth time point based on the second training data (810) described above, as input the amount of discarded badges at a fifth time point, power consumption at a fourth time point prior to the fifth time point, power generation at a fourth time point, and weather data at a fourth time point. At this time, the sixth time point may be a time point after the fifth time point.

[0178] In other words, the second artificial neural network (820) may be a neural network that has learned (or is learning) the correlation between the amount of discarded badges at the second time point, the amount of power consumption at the first time point prior to the second time point, the amount of power generated at the first time point and the weather data at the first time point, the amount of power consumption at the third time point after the second time point and the amount of power generated at the third time point.

[0179] Accordingly, the second artificial neural network (820) according to one embodiment of the present invention can output output data (822) including power consumption at a third time point after the second time point and power generation at a third time point, as input data (821) including the amount of discarded badges at a second time point, power consumption at a first time point prior to the second time point, power generation at a first time point, and weather data at a first time point is input.

[0180] Accordingly, a farm management server (100) according to one embodiment of the present invention inputs input data (821) based on a first time point (T1) and a second time point (T2), and can obtain power consumption and power generation amounts related to a third time point (T2) as outputs.

[0182] A farm management server (100) according to one embodiment of the present invention can acquire first data related to a mushroom farm and second data related to the environment of the mushroom farm (S1020). The following description refers again to FIG. 9.

[0183] At this time, the first data may include, for example, growth status data (Growth_T1) of a mushroom being cultivated at the mushroom farm at a first time point (T1), a first power consumption amount (Power_Con_T1) representing the power consumption of the farm at the first time point (T1), and a first power generation amount (Power_Gen_T1) representing the power generation amount of the farm at the first time point (T1).

[0184] Additionally, the second data may include, for example, first growth environment data (Growth_enviro_T1) representing the growth environment of the mushroom at the first time point (T1) and first weather data (Weather_T1) representing the weather conditions of the mushroom farm.

[0185] A farm management server (100) according to one embodiment of the present invention can generate data by merging the first data and the second data described above. For example, the farm management server (100) can generate merged data that includes all items of the first data and all items of the second data.

[0187] A farm management server (100) according to one embodiment of the present invention can determine the amount of discarded medium (Medium_WT_T2) at a second time point (T2) by inputting first input data, which includes at least a portion of the merged data described above, into a trained first artificial neural network (720). (S1030) At this time, the first input data may include growth status data (Growth_T1), first growth environment data (Growth_enviro_T1), and first weather data (Weather_T1) at a first time point (T1). However, the configuration of such first input data is exemplary and the concept of the present invention is not limited thereto.

[0189] A farm management server (100) according to one embodiment of the present invention inputs a second input data, which includes at least a portion of the amount of discarded medium (Medium_WT_T2) generated by the first artificial neural network (720) and the merged data, into a trained second artificial neural network (820) to determine a second power consumption amount (Power_Con_T3) representing the power consumption amount of the farm at the third time point (T3) and a second power generation amount (Power_Gen_T3) representing the power generation amount of the farm at the third time point (T3). (S1040) At this time, the second input data may include a first power consumption amount (Power_Con_T1), a first power generation amount (Power_Gen_T1), and first weather data (Weather_T1) in addition to the aforementioned amount of discarded medium (Medium_WT_T2).

[0190] Thus, the present invention can predict power generation and power consumption based on the amount of waste media to be generated at a future point in time.

[0192] A farm management server (100) according to one embodiment of the present invention can calculate the surplus power of a mushroom farm at a third time point (T3) based on the second power consumption (Power_Con_T3) and the second power generation (Power_Gen_T3) calculated according to the process described above (S1050). For example, the farm management server (100) can calculate the surplus power of a mushroom farm based on the difference between the second power generation (Power_Gen_T3) and the second power consumption (Power_Con_T3).

[0194] A farm management server (100) according to one embodiment of the present invention can determine the amount of power to be converted into thermal energy among the calculated surplus power (S1060). At this time, the power corresponding to the amount of power to be converted can be converted into thermal energy stored in a space corresponding to the mushroom farm through a heat pump (410) provided in the mushroom farm.

[0195] In this way, when the amount of power generated is greater than the amount of electricity consumed, the surplus energy can be converted into thermal energy and stored in the space of the farm.

[0197] The embodiments 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 on a computer-readable medium. In this case, the medium may be one that stores a computer-executable program. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, flash memory, cloud memory, etc.

[0198] Meanwhile, the above-mentioned computer program may be one specifically designed and configured for the present invention, or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0199] The specific embodiments described in this invention are examples and do not limit the scope of the invention in any way. For the sake of brevity of the specification, descriptions of prior electronic configurations, control systems, software, and other functional aspects of said systems may be omitted. Additionally, the connections of lines or connecting members between components shown in the drawings are illustrative of functional connections and / or physical or circuit connections, and may be replaced or additionally represented as various functional connections, physical connections, or circuit connections in actual devices. Furthermore, unless specifically stated as "essential," "importantly," etc., a component may not be strictly necessary for the application of the invention.

[0200] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0201] 100: Farm Management Server 110: Communications Department 120: 1st processor 130: Memory 140: Second processor 200: User terminal 210: Communications Department 220: Second processor 230: Memory 240: Input / Output Interface 300: Power generation device 400: Environment creation device 510: Badge processing unit 600: Monitoring device Net: Communication network

Claims

Claim 1 A power management method for predicting the amount of waste substrate and the amount of power generated based thereon in an energy-independent farm equipped with a power generation device that generates power using waste substrate, comprising: a step of acquiring first data related to a mushroom farm and second data related to the environment of said mushroom farm, wherein the first data includes growth status data of mushrooms being cultivated in said mushroom farm at a first time point, a first power consumption amount indicating the power consumption of said farm at the first time point, and a first power generation amount indicating the power generation amount of said farm at the first time point, and the second data includes first growth environment data indicating the growth environment of said mushrooms at the first time point and first weather data indicating the weather conditions of said mushroom farm; and a step of determining the amount of waste substrate at a second time point by inputting first input data, which includes at least a portion of data obtained by merging said first data and said second data, into a learned first artificial neural network, wherein said second time point is at least one time point after said first time point, and said amount of waste substrate is used to predict the power consumption and power generation amount at a subsequent time point. A method for managing power in an energy-independent farm utilizing a mushroom substrate, comprising the step of inputting second input data, which includes the amount of discarded substrate and at least a portion of the merged data, into a trained second artificial neural network to determine a second power consumption amount representing the power consumption of the farm at a third point in time and a second power generation amount representing the power generation amount of the farm at the third point in time, wherein the third point in time is at least one point in time after the second point in time. Claim 2 A method for managing power in an energy-independent farm using a mushroom medium according to claim 1, wherein the first input data includes growth state data at the first time point, the first growth environment data, and the first weather data. Claim 3 A method for managing power in an energy-independent farm utilizing a mushroom substrate according to claim 1, wherein the second input data includes the amount of discarded substrate, the first power consumption, the first power generation, and the first weather data. Claim 4 The power management method of an energy-independent farm utilizing a mushroom substrate according to claim 1 further comprises, after the step of determining the second power consumption and the second power generation amount, the step of calculating the surplus power amount of the mushroom farm at the third point in time based on the second power consumption and the second power generation amount; and the step of determining the power amount to be converted into thermal energy among the surplus power; wherein the power corresponding to the power amount to be converted is converted into thermal energy stored in a space corresponding to the mushroom farm through a heat pump provided in the mushroom farm. Claim 5 The power management method of an energy-independent farm utilizing a mushroom medium according to claim 1 further comprises the step of training each of the first artificial neural network and the second artificial neural network prior to the step of acquiring the first data and the second data. Claim 6 A method for managing power in an energy-independent farm utilizing mushroom substrate according to claim 5, wherein the training step comprises the step of training the first artificial neural network using first training data; wherein the first training data includes mushroom growth data at a fourth time point, growth environment data at the fourth time point, and weather data at the fourth time point as first training input data, and includes the amount of discarded substrate at a fifth time point after the fourth time point as first training output data, and the first artificial neural network is a neural network trained to output the first training output data according to the input of the first training input data. Claim 7 A method for managing power in an energy-independent farm utilizing mushroom substrate according to claim 5, wherein the training step comprises the step of training the second artificial neural network using second training data; wherein the second training data includes the amount of discarded substrate at a fifth time point, the amount of power consumption at a fourth time point prior to the fifth time point, the amount of power generated at the fourth time point, and the weather data at the fourth time point as second training input data, and includes the amount of power consumption at a sixth time point and the amount of power generated at the sixth time point as second training output data, and the sixth time point is a time point after the fifth time point; and the second artificial neural network is a neural network trained to output the second training output data according to the input of the second training input data. Claim 8 A method for managing power in an energy-independent farm utilizing a mushroom substrate according to claim 1, wherein the second power generation amount is an amount determined based on the sum of a second-1 power generation amount based on pellets generated from waste substrate and a second-2 power generation amount based on solar energy. Claim 9 A computer program stored on a medium to execute the method of any one of claims 1 to 8 using a computer. Claim 10 In a farm management server for predicting the amount of waste substrate and the amount of power generated based thereon in an energy-independent farm equipped with a power generation device that generates power using waste substrate, the farm management server acquires first data related to a mushroom farm and second data related to the environment of the mushroom farm, wherein the first data includes growth status data of mushrooms being cultivated in the mushroom farm at a first time point, a first power consumption amount representing the power consumption of the farm at the first time point, and a first power generation amount representing the power generation of the farm at the first time point, and the second data includes first growth environment data representing the growth environment of the mushrooms at the first time point and first weather data representing the weather conditions of the mushroom farm, and inputs first input data including at least a portion of data obtained by merging the first data and the second data into a trained first artificial neural network to determine the amount of waste substrate at a second time point, wherein the second time point is at least one time point after the first time point, and the amount of waste substrate is used to predict the power consumption and power generation amount at a subsequent time point, and the amount of waste substrate and the data of the merged data are input into a trained second artificial neural network A farm management server for an energy-independent farm utilizing a mushroom substrate, wherein a second input data including at least a portion is input to determine a second power consumption amount representing the power consumption of the farm at a third point in time and a second power generation amount representing the power generation amount of the farm at the third point in time, and the third point in time is at least one point in time after the second point in time.

Images