Flow-through fish farm energy management and optimization system and operation method

Abstract

The present invention relates to energy management and optimization of a flow-through fish farm. A flow-through fish farm energy management and optimization system according to an embodiment of the present invention comprises: an energy consumption measurement unit for measuring the actual energy consumption of a pump; a water inflow amount prediction unit for predicting water inflow amount on the basis of environmental data; and an operation strategy establishment unit for establishing time period-specific operation strategies including time period-specific outputs for the pump on the basis of the measured actual energy consumption and the predicted water inflow amount.

Description

Energy management and optimization system and operating method for a water-based aquaculture farm

[0001] The present invention relates to energy management and optimization of a flow-through aquaculture farm, and to a technical idea for optimizing the continuous water circulation process of a flow-through aquaculture farm and the resulting energy demand and supply, along with efficient use of energy used in the aquaculture farm, sustainable resource management, and minimization of environmental impact.

[0002] Aquaculture farms can incorporate a variety of sensors to collect real-time data on water temperature, quality, water level, oxygen concentration, and more. IoT technology connects these sensors to a network, enabling real-time monitoring and data collection, contributing to improved energy consumption and production efficiency.

[0003] Conventional aquaculture farm energy management systems face various problems.

[0004] First, limited data analysis makes it difficult to accurately identify energy consumption and production patterns. Furthermore, the system's lack of flexibility hinders its ability to effectively respond to diverse operating conditions and environmental changes at the farm.

[0005] Unnecessary energy consumption leads to inefficient operations, which in turn leads to increased costs and greater environmental impact.

[0006] In particular, existing systems fail to adequately reflect the unique characteristics of flow-through aquaculture farms, making accurate energy optimization difficult. Optimal energy management is difficult because variables such as the aquaculture environment, water temperature, and water quality are not taken into account.

[0007] To address these issues and effectively improve aquaculture energy management, it is necessary to introduce cutting-edge technologies capable of collecting and analyzing more data, enhance system flexibility, implement intelligent control systems that minimize energy consumption, and develop optimization algorithms that take into account the characteristics of flow-through aquaculture farms. This will enable more efficient and sustainable aquaculture operations.

[0008] The present invention aims to improve the energy efficiency of a floating fish farm, reduce operating costs, and enhance environmental sustainability.

[0009] The present invention aims to promote environmental protection through energy consumption optimization.

[0010] The present invention aims to minimize the environmental impact of water use and energy consumption by optimizing energy use in a water-based aquaculture farm.

[0011] The purpose of this invention is to contribute to protecting the natural ecosystem and supporting sustainable aquaculture activities.

[0012] The present invention aims to support aquaculture farm managers in making more accurate and effective decisions through real-time data collection and analysis.

[0013] The present invention aims to improve the efficiency of overall aquaculture farm operation as well as energy management.

[0014] The present invention aims to overcome the limitations of conventional technologies through an adaptive energy optimization algorithm, energy demand prediction, and a customized energy management solution, and to perform energy management more effectively by taking into account the unique operating characteristics of a flowing-water aquaculture farm.

[0015] A system for energy management and optimization of a water-based aquaculture farm according to an embodiment may include an energy consumption measurement unit for measuring actual energy consumption for a pump, an inflow prediction unit for predicting inflow amount based on environmental data, and an operation strategy establishment unit for establishing a time-based operation strategy including time-based output for the pump based on the measured actual energy consumption and the predicted inflow amount.

[0016] The energy consumption measuring unit according to one embodiment collects basic data including power consumption and power factor set at the time of shipment from the factory for each pump, and collects real-time measurement data including real-time power consumption, power factor, and operating status information of each pump through at least one sensor among a vibration sensor, a current sensor, and a temperature sensor installed in each pump, and can calculate the actual energy consumption for each pump based on the collected basic data and the collected real-time measurement data.

[0017] The energy consumption measuring unit according to one embodiment can calculate an average by assigning selected weights to the collected basic data and the collected real-time measurement data, and calculate the actual energy consumption for each pump based on the calculated average.

[0018] The operation strategy establishment unit according to one embodiment collects tidal data and the measured actual energy consumption as the environmental data, preprocesses the collected data, removes missing values ​​or outliers from the preprocessed data, processes the collected data into a format suitable for analysis, and establishes an operation strategy for controlling the output of the pump by time zone by considering the tidal data and the measured actual energy consumption.

[0019] The inflow amount prediction unit according to one embodiment selects a variable according to environmental data as an independent variable, sets the actual energy consumption of the pump as a dependent variable, constructs a linear regression model using the set independent and dependent variables, and can predict the inflow amount using the constructed linear regression model.

[0020] The above-described operation strategy establishment unit according to one embodiment can establish an operation strategy for controlling the rotation rate of a pump based on the predicted inflow amount using the constructed linear regression model.

[0021] According to one embodiment, the inflow amount prediction unit can predict the inflow amount for a specific time period based on tidal data, regardless of the operation of the pump.

[0022] The above-described operation strategy establishment unit according to one embodiment can establish a time-based operation strategy for controlling the time-based output of the pump based on high tide or low tide as the above-described environmental data.

[0023] According to an embodiment, the above-described operation strategy establishment unit can use a linear regression model to predict the energy usage of the pump according to current and future conditions and reflect this in the establishment of the above-described operation strategy by time zone.

[0024] The above-described operation strategy establishment unit according to one embodiment can establish an operation strategy for each time zone, including speed control and operation time adjustment of the pump.

[0025] A system for energy management and optimization of a water-type aquaculture farm according to an embodiment may further include an abnormality diagnosis unit that diagnoses at least one of a failure, a pressure change, and an abnormality in a pipeline by using a decision tree and a random forest algorithm for the actual energy consumption and inflow amount of the pump.

[0026] An operating method of a system for energy management and optimization of a water-type aquaculture farm according to an embodiment may include a step of measuring actual energy consumption for a pump in an energy consumption measurement unit, a step of predicting an inflow amount based on environmental data in an inflow amount prediction unit, and a step of establishing a time-based operation strategy including an output for each time-based time for the pump based on the measured actual energy consumption and the predicted inflow amount in an operation strategy establishment unit.

[0027] In the energy consumption measuring unit according to one embodiment, the step of measuring the actual energy consumption for the pump may include the step of collecting basic data including the power consumption and power factor set at the time of shipment from the factory for each pump, the step of collecting real-time measurement data including the real-time power consumption, power factor, and operating status information for each pump through at least one sensor among a vibration sensor, a current sensor, and a temperature sensor installed in each pump, and the step of calculating the actual energy consumption for each pump based on the collected basic data and the collected real-time measurement data.

[0028] In the above inflow amount prediction unit according to one embodiment, the step of predicting the inflow amount by environmental data may include the step of selecting a variable according to the environmental data as an independent variable, the step of setting the actual energy consumption of the pump as a dependent variable, the step of constructing a linear regression model using the set independent variables and dependent variables, and the step of predicting the inflow amount by using the constructed linear regression model.

[0029] In one embodiment, energy use in aquaculture farms can be optimized to reduce costs and improve energy efficiency.

[0030] In one embodiment, it can promote sustainable aquaculture methods by minimizing environmental impact.

[0031] In one example, optimized energy management can reduce the overall environmental impact of a farm.

[0032] In one example, improving water circulation efficiency in flow-through aquaculture farms can enable more sustainable use of water resources and reduce negative impacts on natural ecosystems.

[0033] In one embodiment, it can prevent energy waste and minimize losses due to pump failure or other operational problems.

[0034] FIG. 1 is a block diagram illustrating an energy management and optimization system for a water-type aquaculture farm according to an embodiment.

[0035] Figure 2 is a diagram illustrating random forest prediction for measuring and improving health based on energy consumption and efficiency.

[0036] Figure 3 is a diagram illustrating the constructed linear regression model.

[0037] Figure 4 is a flowchart for explaining an operation method of a flow-type aquaculture farm energy management and optimization system according to one embodiment.

[0038] Figure 5 is a drawing specifically explaining a method for measuring actual energy consumption for a pump.

[0039] Figure 6 is a drawing specifically explaining a method for predicting the amount of inflow using environmental data.

[0040] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed in this specification are merely illustrative for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described in this specification.

[0041] Embodiments according to the concept of the present invention may have various modifications and take various forms, and thus, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit embodiments according to the concept of the present invention to specific disclosed forms, but rather includes modifications, equivalents, or alternatives that fall within the spirit and technical scope of the present invention.

[0042] While terms such as "first" or "second" may be used to describe various components, these components should not be limited by these terms. These terms are intended solely to distinguish one component from another. For example, a first component may be referred to as a "second component," and similarly, a second component may also be referred to as a "first component," without departing from the scope of the invention.

[0043] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Expressions that describe relationships between components, such as "between," "immediately between," or "directly adjacent to," should be interpreted similarly.

[0044] The terminology used herein is for the purpose of describing specific embodiments only and is not intended to limit the present invention. The singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, it should be understood that the terms "comprises" or "has" are intended to specify the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0045] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0046]

[0047] Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, the scope of the patent application is not limited or restricted by these embodiments. The same reference numerals in each drawing represent the same components.

[0048] FIG. 1 is a block diagram illustrating a flow-type aquaculture farm energy management and optimization system (100) according to one embodiment.

[0049] The present invention optimizes energy use in aquaculture farms, thereby reducing costs and improving energy efficiency. It also minimizes environmental impact, promoting sustainable aquaculture practices. Furthermore, optimized energy management can reduce the overall environmental impact of aquaculture farms.

[0050] To this end, a system (100) for energy management and optimization of a water-type aquaculture farm according to an embodiment may include an energy consumption measurement unit (110), an inflow water quantity prediction unit (120), and an operation strategy establishment unit (130).

[0051] First, the energy consumption measurement unit (110) can measure the actual energy consumption of the pump.

[0052] Measurements can generate quantitative data by detecting the power consumed by a pump in real time while it is in operation. Pumps are a key component in supplying and circulating water from aquaculture farms to aquariums, ensuring efficient water management and a healthy aquaculture environment.

[0053] Energy consumption measurement monitors power consumption during pump operation, and this information can be used later to analyze energy consumption patterns and efficiency. Accurately measuring pump energy consumption can contribute to improving the efficiency of aquaculture operations and minimizing unnecessary energy consumption.

[0054] This measurement information serves as crucial data for the entire aquaculture farm energy management system, identifying optimal operating conditions and optimizing energy consumption. Furthermore, accurate pump energy consumption data can be utilized in future predictive models and automated control systems to support intelligent and efficient aquaculture operations.

[0055] The energy consumption measurement unit (110) can collect basic data including the power consumption and power factor set at the time of factory shipment for each pump.

[0056] The baseline data provides basic performance indicators defined by the manufacturer of each pump, providing fundamental parameters regarding the characteristics and operation of the pump.

[0057] The power consumption set at the factory represents the expected power consumption when the pump is first manufactured and shipped, and is a value set by the manufacturer based on the design and performance of the pump. The energy consumption measurement unit can measure the power consumption while the pump is actually operating based on this value.

[0058] Power factor indicates how effectively a pump utilizes its power, and this value is also provided as a factory preset. The energy consumption measurement unit utilizes this baseline data to monitor and analyze the energy consumption of each pump in real time, thereby optimizing the energy efficiency of the farm.

[0059] In addition, real-time measurement data including real-time power consumption, power factor, and operating status information of each pump can be collected through at least one sensor among the vibration sensor, current sensor, and temperature sensor installed in each pump, and the actual energy consumption for each pump can be calculated based on the collected basic data and the collected real-time measurement data.

[0060] In addition, the energy consumption measurement unit (110) can calculate an average by assigning selected weights to the collected basic data and the collected real-time measurement data, and calculate the actual energy consumption for each pump based on the calculated average.

[0061] A weighted average can be used as a means to more accurately reflect the actual energy consumption for each pump.

[0062] Values ​​collected from baseline data and real-time measurement data are calculated using a weighted average, taking into account their respective importance. Weights are assigned based on key criteria or priorities, reflecting the reliability and importance of each piece of data. The calculated weighted average can be used to fine-tune the actual energy consumption for each pump and analyze accurate energy consumption patterns to support efficient operation.

[0063] Such weighted averaging techniques can accurately determine the energy consumption of each pump system within a farm, help identify optimal operating conditions, and minimize unnecessary energy consumption, thereby improving overall energy efficiency.

[0064] Next, the inflow amount prediction unit (120) can predict the inflow amount based on environmental data.

[0065] Environmental data can include information such as weather conditions, rainfall, water levels, and tides. Based on this data, the inflow forecasting unit can predict water volumes over a certain period of time, supporting water management in aquaculture farms.

[0066] Environmental data can be collected through weather stations, hydrological observation devices, and other sensors, and is collected in real time, and the inflow amount prediction unit (120) utilizes this data to accurately predict the inflow amount.

[0067] According to an embodiment, the inflow amount prediction unit (120) selects a variable according to environmental data as an independent variable, sets the actual energy consumption of the pump as a dependent variable, and can build a linear regression model using the set independent and dependent variables.

[0068] Additionally, the inflow amount can be predicted using the constructed linear regression model.

[0069] To this end, the inflow prediction unit (120) selects variables judged to affect the inflow amount from among the surrounding environment data as independent variables, and sets the actual energy consumption of the pump as a dependent variable.

[0070] The process of building a linear regression model using selected independent and dependent variables allows for the optimal model to be found by considering the data's characteristics and relationships. This model represents a linear relationship between the given environmental data and the pump's energy consumption.

[0071] Once the model is built, the pump's expected energy consumption can be calculated using the given environmental data as input. This allows the inflow prediction unit (120) to predict future inflows in response to changing environmental conditions, contributing to optimizing water management in the aquaculture farm.

[0072] The inflow amount prediction unit (120) according to one embodiment can predict the inflow amount for a specific time period based on tidal data regardless of the operation of the pump.

[0073] That is, even if the pump is not operating, it is possible to predict changes in the amount of water according to environmental conditions, and the tidal data indicates the tidal state of the environment, which may include weather conditions, rainfall, water level, etc. The inflow amount prediction unit (120) can utilize this tidal data to predict the amount of water that will flow into the fish farm for a specific time period.

[0074] In addition, the operation strategy establishment unit (130) can establish an operation strategy for each time zone, including the output for each time zone for the pump, based on the measured actual energy consumption and the predicted inflow amount.

[0075] Operating strategies can determine the efficient operation of each pump by considering the correlation between measured energy consumption and predicted inflow. Specifically, environmental data can be considered to optimize aquaculture operations by establishing strategies such as maintaining high or low pump output during certain times.

[0076] The operational strategy establishment unit (130) according to one embodiment can collect tidal data and measured actual energy consumption as environmental data, preprocess them, remove missing values ​​or outliers from the preprocessed data, and process them into a format suitable for analysis.

[0077] Additionally, considering tidal data and measured actual energy consumption, an operating strategy can be established to adjust the pump output by time zone.

[0078] An operation strategy establishment unit (130) according to an embodiment can establish an operation strategy for controlling the rotation rate of a pump based on the predicted inflow amount using the constructed linear regression model.

[0079] The linear regression model represents the relationship between the surrounding environmental data and the energy consumption of the pump, so the predicted inflow can be used to determine the appropriate pump rotation rate at a specific time period.

[0080] The operational strategy established by the Operation Strategy Establishment Unit (130) aims to ensure efficient pump operation based on the predicted inflow volume. For example, when a high inflow volume is predicted, a strategy can be established to increase the pump rotation rate to ensure efficient water management. Conversely, when a low inflow volume is predicted, a strategy can be established to reduce the pump rotation rate to conserve energy.

[0081] The operational strategy establishment unit (130) according to an embodiment can control the output of the pump by time zone based on high tide or low tide as environmental data.

[0082] High tide and low tide are important indicators of tidal conditions. Low tide is a phenomenon in which the sea level drops, and high tide is a phenomenon in which the sea level rises.

[0083] Using high and low tides as environmental data, we can predict the amount of water flowing into the fish farm or changes in water level. This allows us to determine the level of water needed at a given time and adjust pump output accordingly. For example, during high tide, the pressure of the incoming seawater is high, so a lower output is sufficient to ensure sufficient inflow. In this case, pump output can be reduced to supply water to the fish farm, saving energy.

[0084] According to one embodiment, the operational strategy formulation unit (130) can use a linear regression model to predict pump energy usage based on current and future conditions, and reflect this in the formulation of the time-based operational strategy. Furthermore, a time-based operational strategy can be formulated that includes pump speed control and operating time adjustment.

[0085] The linear regression model represents a linear relationship between the surrounding environmental data and the energy consumption of the pump, so the expected energy consumption of the pump can be predicted through the model.

[0086] This allows the operational strategy development unit (130) to adjust operational strategies for each time zone based on predicted energy usage. For example, during times when energy usage is predicted to be high, pump speeds can be reduced or operating hours adjusted to optimize energy consumption.

[0087] In addition, the energy management and optimization system (100) for a water-type fish farm according to one embodiment may further include an abnormality diagnosis unit (140).

[0088] An abnormality diagnosis unit (140) according to an embodiment can diagnose at least one of a failure, a pressure change, and an abnormality in a pipeline by utilizing a decision tree and random forest algorithms for the actual energy consumption and inflow amount of the pump.

[0089] Decision tree and random forest algorithms are effective at learning the relationships between various variables and detecting anomalies based on criteria. Pump energy consumption and inflow are important system indicators, allowing for accurate assessment of pump status.

[0090] The control unit (150) according to one embodiment can be interpreted as a central processing unit (CPU) and can perform various operations and process data within the system.

[0091] In particular, the control unit (150) can read commands from memory, interpret and execute the commands, and can also perform arithmetic operations such as addition, subtraction, multiplication, and division.

[0092] In addition, the control unit (150) can handle data storage and retrieval, and can also perform the function of reading data from memory and storing the results of performing operations back into memory.

[0093] In addition, the control unit (150) can manage the execution flow of the program, and in particular, can control the flow of the program using commands such as conditional statements (if-else) or iterative statements (for, while). In addition, the control unit (150) can have a small and fast memory device called a register placed inside, and this register can be used to temporarily store data or perform operations.

[0094] The control unit (150) can process and take appropriate action when an external event or exceptional situation occurs, and can quickly access data and instructions by using cache memory that is faster than the main memory.

[0095] In addition, the control unit (150) can use a system bus to communicate with memory or input / output devices, and can provide various power management functions to minimize power consumption.

[0096] Figure 2 is a diagram illustrating random forest prediction (200) for measuring and improving health based on energy consumption and efficiency.

[0097] Random forests can be effectively utilized in various aspects of energy management and optimization technology in aquaculture farms.

[0098] Random forests can be used to predict pump energy consumption. This allows for in-depth predictions of how much energy will be consumed at a given time.

[0099] Bootstrap sampling allows us to input test samples reflecting various pump operating conditions and environmental variables, and random feature selection allows us to maintain the independence between trees (trees 1, 2, and 600) to improve model accuracy.

[0100] Random forests can be used to predict water inflow based on environmental data. This helps accurately predict the amount of water required for aquaculture operations.

[0101] By learning the relationship between the pump's energy consumption and inflow volume, prediction accuracy for various environmental conditions can be improved.

[0102] By utilizing random forests, abnormality diagnosis can be performed on the actual energy consumption and inflow volume of the pump, and early response can be made by determining whether there is a pump failure, pressure change, or pipeline abnormality.

[0103] Diversity across multiple trees and random feature selection allows the model to robustly identify a variety of anomalies.

[0104] Prediction and diagnosis using random forests can improve energy efficiency in aquaculture farms and optimize maintenance time through fault prediction, thereby enhancing productivity and stability.

[0105] The present invention utilizes decision trees and random forests to intelligently diagnose the condition of a pump. Specifically, decision tree and random forest algorithms can be used to intelligently diagnose pump failures, inflow pressure changes, and pipeline abnormalities.

[0106] The present invention utilizes decision trees and random forests to analyze measured and baseline data, enabling precise diagnosis of pump condition and prediction of necessary maintenance measures. This allows for a more refined assessment of pump health and enables intelligent measures for preventive maintenance and operational optimization.

[0107] Data collected from pumps includes power consumption, power factor, operating hours, inlet pressure, and other performance indicators. The collected data can be cleaned to remove missing values ​​or outliers and processed into a form suitable for analysis.

[0108] To build decision tree and random forest models, important features must be selected. These may include variables related to pump efficiency, performance degradation, and maintenance requirements.

[0109] In the present invention, a data set is prepared based on selected characteristics and can be used for model learning.

[0110] In particular, decision tree and random forest algorithms can be used to train models, in which the models learn how to accurately classify and predict various pump states.

[0111] The model can distinguish between different states of the pump, such as normal operation, minor problems, and serious failures.

[0112] Furthermore, the trained model can diagnose the current status of the pump based on real-time collected data and predict potential problems. For example, it can identify changes in inlet pressure or pipe abnormalities, predict the likelihood of pump failure, and take proactive measures.

[0113] By interpreting the results from the model, specific actions can be taken. For example, specific pumps can be identified for maintenance, operating mode adjustments can be made, and energy usage can be optimized.

[0114] Meanwhile, each collected data (consumption, power factor, operating time, inflow water pressure, etc.) can be organized into a tree structure of values ​​to find the final designated predicted value.

[0115] The final prediction value can be obtained by using a decision tree because there can be numerous results such as normal operation of the pump, minor problems, serious failures, abnormalities in the pipeline, and changes in the inflow water pressure.

[0116] Figure 3 is a drawing explaining the constructed linear regression model (300).

[0117] Pump operation can be adjusted based on the tidal influences of the moon and sun. However, fish farm operators will likely want to maintain a fixed daily water flow rate.

[0118] The positions of the moon and the sun and their gravitational interactions cause tides, which greatly influence the amount of ocean water flowing into the ocean.

[0119] By collecting tidal data and analyzing the positions of the moon and sun and the tidal patterns to build a linear regression model (300), it can be used as important basic information for determining pump operation strategies.

[0120] The present invention utilizes a linear regression model to predict pump energy usage based on current and future conditions. For example, the inflow rate and the resulting pump energy usage can be predicted based on tidal changes.

[0121] Pump operation can be adjusted based on predicted data to maximize energy efficiency. This can include adjusting pump speed and operating hours, contributing to reduced energy consumption and lower operating costs.

[0122] Based on the prediction results of the linear regression model, strategies to optimize energy use can be developed and implemented, which will also help in establishing long-term energy management plans.

[0123] The linear regression model according to the present invention is continuously updated with real-time data, which allows for continuous adjustment of energy management strategies in response to changing conditions in the aquaculture farm.

[0124] Pump operations that take into account the influence of tidal fluctuations can be managed in an integrated manner with the operations of other pumps in the aquaculture farm, and a linear regression model can model the linear relationship between these variables by analyzing energy usage data, inflow volume, and pump operating status of the aquaculture pumps.

[0125] Based on the analyzed data and model predictions, aquaculture managers can make pump maintenance schedules, energy usage optimization strategies, and other operational decisions.

[0126] To this end, the present invention collects tidal data (moon and sun positions and tidal patterns) and pump operation data (energy consumption, operating time, etc.), preprocesses the collected data to remove missing values ​​or outliers, and processes the data into a form suitable for analysis.

[0127] Additionally, to understand the relationship between the tidal effects and the energy consumption of the pump, relevant variables (e.g., lunar cycle, solar position, water inflow) can be selected and these variables can be set as independent variables, with the energy consumption of the pump as the dependent variable.

[0128] In the present invention, a linear regression model can be constructed using selected variables, and this model can be used to predict the effect of tidal changes on the energy usage of a pump.

[0129] The model estimates the coefficients of each variable, allowing analysis of how each factor affects pump energy use.

[0130] Additionally, the model creates a linear equation (Y=aX+b+ε) while organizing each data. By utilizing the slope of this model, etc., it is possible to determine whether to reduce the pump rotation rate based on the observation that the flow rate will continue to increase.

[0131] If the slope of the first equation (Y=aX+b+ε) is opposite, you can decide whether to increase the rotational speed of the pump.

[0132] The present invention can evaluate the accuracy and predictive ability of a constructed model. To do this, a test data set can be used or a cross-validation method can be applied. The model's performance can be verified as satisfactory and adjusted as needed.

[0133] By applying the model to real-time data, the energy usage of the pump can be predicted, and based on the predicted energy usage, the operating time, speed, and capacity of the pump can be adjusted to optimize energy usage.

[0134] The model is continuously updated and can be adjusted based on new data. Furthermore, pump operating strategies can be continuously optimized in response to changing conditions.

[0135] Figure 4 is a flowchart for explaining an operation method of a flow-type aquaculture farm energy management and optimization system according to one embodiment.

[0136] In an embodiment, the operating method of a system for energy management and optimization of a water-type aquaculture farm can measure actual energy consumption for a pump in an energy consumption measurement unit (step 401).

[0137] The system can utilize an energy consumption measurement unit to measure the energy consumption of each pump. Specifically, the system can measure the power consumption and power factor generated during pump operation in real time to obtain actual energy consumption data. The collected data can be used for system learning and prediction.

[0138] Additionally, the inflow prediction unit can predict inflow based on environmental data (step 402). The inflow prediction unit predicts the amount of water flowing into the aquaculture farm based on given environmental data. Specifically, environmental data can include various variables such as tidal data, weather information, and seasonality. This environmental data is used as input variables, assigned a predetermined weighting, and a linear regression model is used to predict inflow.

[0139] In addition, the method of operating the energy management and optimization system for a water-type aquaculture farm according to an embodiment of the present invention can establish an operation strategy for each time zone, including an output for each time zone for the pump, based on the measured actual energy consumption and the predicted inflow amount, in the operation strategy establishment unit (step 403).

[0140] The Operational Strategy Development Department utilizes measured actual energy consumption and predicted inflow to develop operational strategies that adjust the output of each pump based on time of day. Measured energy consumption indicates energy efficiency, while predicted inflow can reflect the water volume of the basin based on environmental conditions.

[0141] Predictions based on linear regression models and various data inputs are used to determine the optimal output for pump operation, and time-based operating strategies can increase energy efficiency and minimize unnecessary energy consumption by adjusting the pump's rotation rate, operating time, etc.

[0142] Figure 5 is a drawing specifically explaining a method for measuring actual energy consumption for a pump.

[0143] In the energy consumption measurement unit, basic data including the factory-set power consumption and power factor for each pump can be collected to measure the actual energy consumption for the pump (step 501).

[0144] Next, real-time measurement data including real-time power consumption, power factor, and operating status information of each pump can be collected through at least one sensor among the vibration sensor, current sensor, and temperature sensor installed in each pump (step 502).

[0145] Additionally, based on the collected basic data and the collected real-time measurement data, the actual energy consumption for each pump can be calculated (step 503).

[0146] Figure 6 is a drawing specifically explaining a method for predicting the amount of inflow using environmental data.

[0147] To predict the inflow volume based on environmental data, the present invention selects variables based on the environmental data as independent variables (step 601). Furthermore, the actual energy consumption of the pump is set as a dependent variable (step 602), and a linear regression model can be constructed using the set independent and dependent variables (step 603).

[0148] In addition, in the present invention, the inflow amount can be predicted using the constructed linear regression model (step 604).

[0149] Ultimately, the present invention can optimize energy use in aquaculture farms, thereby reducing costs and improving energy efficiency.

[0150] Additionally, it can promote sustainable aquaculture practices by minimizing environmental impact, and optimized energy management can reduce the overall environmental impact of aquaculture farm.

[0151] Moreover, improving water circulation efficiency in flow-through aquaculture farms can enable more sustainable use of water resources, reduce negative impacts on natural ecosystems, prevent energy waste, and minimize losses due to pump failures or other operational issues.

[0152]

[0153] The devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0154] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0155] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0156] Although the embodiments described above have been described with limited drawings, those skilled in the art will recognize that various modifications and variations can be made based on the above description. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0157] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. Energy consumption measuring unit that measures the actual energy consumption of the pump; An inflow prediction unit that predicts the inflow amount based on environmental data; and An operation strategy establishment department that establishes a time-based operation strategy including time-based output for the pump based on the measured actual energy consumption and the predicted inflow amount. A system for energy management and optimization of a hydroponic farm, comprising:

2. In paragraph 1, The above energy consumption measuring unit, Collect baseline data including factory-set power consumption and power factor for each pump, Real-time measurement data including real-time power consumption, power factor, and operating status information of each pump is collected through at least one sensor among the vibration sensor, current sensor, and temperature sensor installed on each pump. A system for energy management and optimization of a floating fish farm, characterized in that it calculates actual energy consumption for each pump based on the collected basic data and the collected real-time measurement data.

3. In paragraph 2, The above energy consumption measuring unit, A system for energy management and optimization of a flowing-type aquaculture farm, characterized in that it calculates an average by assigning selected weights to each of the collected basic data and the collected real-time measurement data, and calculates the actual energy consumption for each pump based on the calculated average.

4. In paragraph 1, The above operational strategy establishment department, As the above environmental data, tidal data and the measured actual energy consumption are collected and preprocessed. Remove missing values ​​or outliers from the above preprocessed data and process it into a format suitable for analysis. A system for energy management and optimization of a floating fish farm, characterized in that it establishes an operating strategy for controlling the output of a pump by time zone by considering the above tidal data and the measured actual energy consumption.

5. In paragraph 1, The above inflow prediction section is, Select variables based on environmental data as independent variables, The actual energy consumption of the above pump is set as a dependent variable, A system for energy management and optimization of a flow-through aquaculture farm, characterized in that a linear regression model is constructed using the independent and dependent variables set above, and the inflow amount is predicted using the constructed linear regression model.

6. In paragraph 5, The above operational strategy establishment department, A system for energy management and optimization of a flowing-type aquaculture farm, characterized in that an operational strategy for controlling the rotation rate of a pump is established based on the predicted inflow amount using the linear regression model constructed above.

7. In paragraph 1, The above inflow prediction section is, A flow-type aquaculture farm energy management and optimization system characterized by predicting the inflow amount at a specific time period based on tidal data regardless of the operation of the above pump.

8. In paragraph 1, The above operational strategy establishment department, A system for energy management and optimization of a flowing-type aquaculture farm, characterized by establishing a time-based operation strategy for controlling time-based output of a pump based on high tide or low tide as the above environmental data.

9. In paragraph 1, The above operational strategy establishment department, A system for energy management and optimization of a floating fish farm, characterized in that it predicts the energy usage of a pump according to current and future conditions using a linear regression model and reflects this in establishing an operation strategy for each time period.

10. In paragraph 1, The above operational strategy establishment department, A system for energy management and optimization of a floating fish farm characterized by establishing a time-based operating strategy including speed control and operating time adjustment of the above pump.

11. In paragraph 1, An abnormality diagnosis section that diagnoses at least one of the following: failure, pressure change, or pipeline abnormality, using decision tree and random forest algorithms for the actual energy consumption and inflow amount of the above pump. A system for energy management and optimization of a hydroponic farm, characterized by further comprising:

12. In the energy consumption measurement unit, a step of measuring the actual energy consumption for the pump; In the inflow amount prediction section, a step of predicting the inflow amount based on environmental data; and In the operation strategy establishment department, a step of establishing a time-based operation strategy including time-based output for the pump based on the measured actual energy consumption and the predicted inflow amount A method of operating a flow-type aquaculture farm energy management and optimization system, characterized by including a.

13. In paragraph 12, In the energy consumption measuring unit above, the step of measuring the actual energy consumption for the pump is: A step of collecting baseline data including factory-set power consumption and power factor for each pump; A step of collecting real-time measurement data including real-time power consumption, power factor, and operating status information of each pump through at least one sensor among a vibration sensor, a current sensor, and a temperature sensor installed in each of the above pumps; and Step of calculating actual energy consumption for each pump based on the collected basic data and the collected real-time measurement data. A method of operating a flow-type aquaculture farm energy management and optimization system, characterized by including a.

14. In paragraph 12, In the above inflow prediction section, the step of predicting the inflow amount using environmental data is: A step for selecting variables based on environmental data as independent variables; A step of setting the actual energy consumption of the above pump as a dependent variable; A step of constructing a linear regression model using the independent and dependent variables set above; and Step for predicting the inflow amount using the linear regression model constructed above A method of operating a flow-type aquaculture farm energy management and optimization system, characterized by including a.

Images