Method and device for optimizing distributed power for building

Abstract

The present invention relates to a method and device for optimizing the distributed power for a building. According to an embodiment of the present invention, the method for optimizing the distributed power for a building comprises the steps of: collecting energy usage data of a building and confirming an energy usage pattern through data analysis of the collected energy usage data; predicting energy demand by using a trained demand prediction model; and optimizing the combination of distributed power applied to the building by using a genetic algorithm on the basis of the confirmed energy usage pattern and the predicted energy demand.

Description

Method and device for optimizing distributed power generation in buildings

[0001] The present invention relates to a method and device for optimizing distributed power generation in a building, and more particularly, to a method and device for optimizing distributed power generation in a building for optimizing a combination of distributed power generation according to the energy usage pattern of the building.

[0002] Research related to this patent was conducted with the support of the Korea Institute of Energy Technology Evaluation and Planning (Research Project Name: Energy International Joint Research (ETP), Research Project Name: Demonstration of a Southeast Asian Local Customized Model Based on Korean BEMS Standards for Distributed Power Generation, Project Unique Number: 1415186719, Project Number: 20218510010130) under the supervision of the Ministry of Trade, Industry and Energy.

[0003] Buildings operate using a variety of energy sources, most notably electricity, water, gas, and heat.

[0004] The technology and market for applying distributed power sources that incorporate renewable energy to such buildings are growing to meet policies such as eco-friendly buildings and zero-energy buildings, and to meet the global demand for carbon neutrality.

[0005] As such, interest in distributed power generation is growing, and the complexity of distributed power systems is steadily increasing. Therefore, technologies are needed that optimize the characteristics of distributed power generation systems combining multiple renewable energy sources and manage their storage and consumption more efficiently.

[0006] However, while control and prediction technologies for multiple distributed power sources are being developed, even when multiple distributed power sources are combined, power generation control is limited to individual distributed power sources. The selection of distributed power sources generally focuses solely on reducing power consumption. In other words, there are no established criteria for selecting the optimal distributed power source.

[0007] Embodiments of the present invention aim to provide a method and device for optimizing distributed power generation in a building, for optimizing a combination of distributed power sources according to the energy usage pattern of the building.

[0008] Embodiments of the present invention aim to provide a method and device for optimizing distributed power generation in a building, which optimizes a combination of distributed power sources applied to a building using a genetic algorithm based on energy usage patterns and energy demands.

[0009] Embodiments of the present invention aim to provide a method and device for optimizing distributed power generation in a building, which increases the possibility of finding a global optimum solution without falling into a local optimum solution during the process of deriving an optimum solution for a distributed power generation combination.

[0010] However, the problem to be solved by the present invention is not limited to this, and may be expanded in various ways in environments that do not deviate from the spirit and scope of the present invention.

[0011] According to one embodiment of the present invention, a distributed power optimization method for a building performed by a distributed power optimization device may be provided, the method including the steps of collecting energy usage data of a building and confirming an energy usage pattern through data analysis of the collected energy usage data; predicting energy demand using a pre-learned demand prediction model; and optimizing a distributed power combination applied to the building using a genetic algorithm based on the confirmed energy usage pattern and the predicted energy demand.

[0012] The step of optimizing the above distributed power source combination may be performed by using the genetic algorithm to optimize an initial distributed power source combination randomly generated for a gene composed of at least one of solar energy, fuel cells, combined heat and power generation, and energy storage devices.

[0013] The step of optimizing the above distributed power source combination can calculate a fitness function in the genetic algorithm by evaluating the energy efficiency, cost, and CO2 emissions of the distributed power source combination.

[0014] The step of optimizing the above distributed power generation combination can adjust the influence of each of energy efficiency, cost, and CO2 emissions on the suitability of the distributed power generation combination by adjusting each weight applied to the energy efficiency, cost, and CO2 emissions of the distributed power generation combination in the genetic algorithm.

[0015] The step of optimizing the above distributed power generation combination may include setting a weight corresponding to the highest priority element of the fitness function in the genetic algorithm among the energy efficiency, cost, and CO2 emissions of the distributed power generation combination in the genetic algorithm to be greater than the remaining weights.

[0016] The step of optimizing the above distributed power combination may include randomly resetting the value of each gene within a specific range for some genes among the distributed power combinations in the genetic algorithm or mutating the genes by adding or subtracting a specific value from the current value of each gene.

[0017] The step of optimizing the above distributed power combination can optimize the distributed power combination by repeating the genetic algorithm until a certain number of generations or until the fitness function converges.

[0018] Meanwhile, according to another embodiment of the present invention, a device for optimizing distributed power generation in a building may be provided, comprising: a communication module for communicating with a distributed power generation applied to a building; a memory for storing one or more programs; and a processor for executing the one or more stored programs, wherein the processor collects energy usage data of the building, identifies an energy usage pattern through data analysis of the collected energy usage data, predicts energy demand using a learned demand prediction model, and optimizes a distributed power generation combination applied to the building using a genetic algorithm based on the identified energy usage pattern and the predicted energy demand.

[0019] The above processor can optimize a randomly generated initial distributed power source combination for a gene comprising at least one of solar energy, fuel cell, combined heat and power generation, and energy storage devices using the genetic algorithm.

[0020] The above processor can calculate a fitness function in the genetic algorithm by evaluating the energy efficiency, cost, and CO2 emissions of the distributed power generation combination.

[0021] The above processor can adjust the influence of each of energy efficiency, cost, and CO2 emissions on the suitability of the distributed power source combination by adjusting the respective weights applied to each of the energy efficiency, cost, and CO2 emissions of the distributed power source combination in the genetic algorithm.

[0022] The above processor can set a weight corresponding to a top priority element of a fitness function in the genetic algorithm among energy efficiency, cost, and CO2 emissions of a distributed power source combination in the genetic algorithm to be greater than the remaining weights.

[0023] The above processor can randomly reset the value of each gene within a specific range for some genes among the distributed power combinations in the genetic algorithm or mutate them by adding or subtracting a specific value from the current value of each gene.

[0024] The above processor can optimize the distributed power combination by repeating the process until a certain number of generations or a fitness function converges in the genetic algorithm.

[0025] The disclosed technology may have the following effects. However, this does not mean that a particular embodiment must include all or only the following effects, and thus the scope of the disclosed technology should not be construed as being limited thereby.

[0026] Embodiments of the present invention can optimize the distributed power generation combination according to the energy usage pattern of a building.

[0027] Embodiments of the present invention can optimize a distributed power generation combination applied to a building using a genetic algorithm based on energy usage patterns and energy demands.

[0028] Embodiments of the present invention can increase the possibility of finding a global optimum solution without falling into a local optimum solution during the process of deriving an optimization of a distributed power source combination.

[0029] FIG. 1 is a configuration diagram of a distributed power optimization system for a building according to one embodiment of the present invention.

[0030] Figure 2 is a flowchart illustrating a method for optimizing distributed power supply of a building according to one embodiment of the present invention.

[0031] FIG. 3 is a diagram illustrating a genetic algorithm performed by a distributed power optimization device according to one embodiment of the present invention.

[0032] Figure 4 is a configuration diagram of a distributed power optimization device for a building according to one embodiment of the present invention.

[0033] The present invention is capable of various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and it is to be understood that all modifications, equivalents, and alternatives included within the technical spirit and scope of the present invention are included. In describing the present invention, if a detailed description of a related known technology is judged to obscure the gist of the present invention, the detailed description will be omitted.

[0034] Terms like "first" and "second" may be used to describe various components, but these terms do not limit the components themselves. These terms are used solely to distinguish one component from another.

[0035] The terminology used in this invention is solely for the purpose of describing specific embodiments and is not intended to limit the invention. The terminology used in this invention has been selected from widely used, current terms, taking into account the functions of the invention. However, this may vary depending on the intentions of those skilled in the art, precedents, or the emergence of new technologies. Furthermore, in certain cases, the applicant may arbitrarily select terms, in which case their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this invention should not be defined simply as names of terms, but rather based on their meanings and the overall content of the invention.

[0036] Singular expressions include plural expressions unless the context clearly dictates otherwise. In the present invention, terms such as "comprise" or "have" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood not to preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0037] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. In describing with reference to the attached drawings, identical or corresponding components are assigned the same drawing numbers, and redundant descriptions thereof will be omitted.

[0038] FIG. 1 is a configuration diagram of a distributed power optimization system for a building according to one embodiment of the present invention.

[0039] As illustrated in FIG. 1, a distributed power optimization system (100) for a building according to an embodiment of the present invention includes a distributed power source (110) and a distributed power optimization device (120). However, not all of the illustrated components are essential. The distributed power optimization system (100) may be implemented with more components than the illustrated components, or may be implemented with fewer components.

[0040] Below, the specific configuration and operation of each component of the distributed power optimization system (100) of the building of Fig. 1 are described.

[0041] A distributed power source (110) refers to a power generation facility that generates power using distributed power sources such as photovoltaic (PV) power generation, fuel cells (FC), combined heat and power (CHP), and energy storage systems (ESS). The distributed power source (110) may include power sources that can generate different types of distributed resources. Additionally, the distributed power source (110) may include a configuration that can convert natural energy into electrical energy or thermal energy. In one embodiment of the present invention, the distributed power source (110) may include at least one distributed power source among solar power generation (111), fuel cells (112), combined heat and power generation (113), and energy storage devices (114). Here, the energy storage devices store energy by charging the power generated by the distributed power source (110) into a battery. The energy storage devices (114) may discharge the battery under the control of the distributed power optimization device (120) and supply the stored power to a load or the power grid. The energy storage device may include a battery, a power conditioning system (PCS), and a battery management system (BMS).

[0042] The load (130) represents a load resource or load facility that consumes the power generated by the power generation resource of the distributed power source (110). For example, the load (130) may represent a consumer consuming power in a building. The load (130) represents a facility that consumes power, such as a home, building, or factory. The load (130) may be a household or industrial facility that consumes power, and specific requirements, such as the required power amount and voltage, may vary depending on the type and time of each consumer.

[0043] According to one embodiment of the present invention, a distributed power optimization device (120) for a building can collect energy usage data (e.g., electricity, heat, etc.) of the building and analyze energy usage patterns through data analysis of the energy usage data. Here, the distributed power optimization device (120) can identify daily, monthly, or seasonal energy usage patterns through data analysis.

[0044] The distributed energy optimization device (120) can predict future energy demand using a pre-trained machine learning model (e.g., a demand prediction model). The distributed energy optimization device (120) can build a demand prediction model based on past data. For example, the distributed energy optimization device (120) can build a demand prediction model based on time series analysis or LSTM.

[0045] Thereafter, the distributed power optimization device (120) can optimize the distributed power combination applied to the building using a genetic algorithm based on the identified energy usage pattern and predicted energy demand. That is, the distributed power optimization device (120) can optimize an appropriate distributed power combination based on the identified energy usage pattern and predicted energy demand. For example, a genetic algorithm may be used as the optimization algorithm.

[0046] In this way, the distributed power optimization device (120) can set an appropriate combination of distributed power sources (e.g., solar power, fuel cell, CHP, ESS, etc.) according to the energy usage pattern of the building by considering various factors.

[0047] To this end, a distributed power optimization device (120) analyzes energy usage patterns, and analysis of the usage patterns can be performed according to a distributed power optimization method as in FIG. 2.

[0048] Figure 2 is a flowchart illustrating a method for optimizing distributed power supply of a building according to one embodiment of the present invention.

[0049] In step S101, the distributed power optimization device (120) collects energy usage data of the building.

[0050] In step S102, the distributed power optimization device (120) identifies the energy usage pattern through data analysis of the collected energy usage data.

[0051] In step S103, the distributed power optimization device (120) predicts energy demand using a pre-learned demand prediction model.

[0052] In step S104, the distributed power optimization device (120) optimizes the distributed power combination applied to the building using a genetic algorithm based on the identified energy usage pattern and predicted energy demand.

[0053] FIG. 3 is a diagram illustrating a genetic algorithm performed by a distributed power optimization device according to one embodiment of the present invention.

[0054] A distributed power optimization device (120) according to one embodiment of the present invention optimizes distributed power source combinations using a genetic algorithm. Referring to FIG. 3, the process of setting an appropriate distributed power source according to a building's energy usage pattern will be described based on the basic genetic algorithm flow.

[0055] In step S201, the distributed power optimization device (120) according to one embodiment of the present invention performs an initialization operation. The distributed power optimization device (120) sets an initial population in a genetic algorithm. The distributed power optimization device (120) randomly generates an initial distributed power combination. In the initialization operation, the distributed power optimization device (120) randomly generates an initial combination of distributed power sources (e.g., solar power, fuel cells, combined heat and power (CHP), energy storage systems (ESS), etc.).

[0056] In step S202, the distributed power optimization device (120) according to one embodiment of the present invention performs a fitness evaluation operation. The distributed power optimization device (120) defines a fitness function and evaluates the defined fitness. The distributed power optimization device (120) calculates the fitness of each distributed power combination. In the fitness evaluation operation, the distributed power optimization device (120) evaluates the energy efficiency, cost, and CO2 emissions of each distributed power combination to calculate the fitness function.

[0057] In step S203, the distributed power optimization device (120) according to one embodiment of the present invention performs a selection operation. The distributed power optimization device (120) applies a method for selecting a distributed power combination. The distributed power optimization device (120) selects a distributed power combination with a high degree of fitness. In the selection operation, the distributed power optimization device (120) selects a distributed power combination with a high degree of fitness and transmits it to the next generation.

[0058] In steps S204 and S205, the distributed power optimization device (120) according to one embodiment of the present invention performs crossover and mutation operations. The distributed power optimization device (120) applies the crossover method to cross the selected parent distributed power combinations to generate offspring. In addition, the distributed power optimization device (120) applies the mutation method to mutate some genes of the offspring distributed power combinations. The distributed power optimization device (120) generates a new distributed power combination through crossover and mutation operations on the distributed power combinations selected in the crossover and mutation operations.

[0059] In step S206, the distributed power optimization device (120) according to one embodiment of the present invention performs a termination condition check operation. The distributed power optimization device (120) checks the termination condition (e.g., number of generations, convergence of fitness, etc.) for the genetic algorithm. If the termination condition is satisfied, the distributed power optimization device (120) derives an optimal distributed power combination and then terminates the genetic algorithm. The distributed power optimization device (120) repeats from step S202 until a certain number of generations or a fitness function converges in the preset termination condition check operation. Here, if the termination condition is not satisfied, the distributed power optimization device (120) returns to step S202 and generates the next generation.

[0060] In step S207, the distributed power optimization device (120) according to one embodiment of the present invention performs a selection completion operation. If a preset termination condition is satisfied in the selection completion operation, the distributed power optimization device (120) derives an optimal distributed power combination.

[0061] Hereinafter, a genetic algorithm applied to one embodiment of the present invention will be described in detail.

[0062] In terms of the initialization operation, the distributed power optimization device (120) randomly generates an initial distributed power combination. Here, each distributed power combination can be expressed as a chromosome composed of solar power, fuel cells, combined heat and power (CHP), and ESS. Each gene can represent the installation capacity and operation strategy of the corresponding distributed power generation.

[0063] Next, regarding the fitness evaluation operation, the distributed power optimization device (120) evaluates the fitness of each distributed power combination. Here, the fitness function can be calculated based on energy efficiency, cost, and CO2 emissions. For example, the fitness function can be calculated as follows.

[0064] Fitness function example: Fitness = a × energy efficiency - b × cost - c × CO2 emissions

[0065] Here, a, b, and c used in the genetic algorithm's fitness function can be weights that adjust the importance of each factor. They can be used to balance the impact of each fitness factor on fitness.

[0066] Specifically, "a" represents the energy efficiency weighting factor. Here, energy efficiency indicates how efficiently a distributed power system uses energy. Higher energy efficiency means that the same task can be performed with less energy, or more tasks can be performed with the same amount of energy.

[0067] a can moderate the impact of energy efficiency on overall fitness. The higher a, the more energy-efficient the system is, and the higher the fitness.

[0068] And b represents the cost weighting. Here, cost includes the initial installation cost, operation, and maintenance costs of distributed power generation. A lower cost indicates greater economic advantage.

[0069] b can modulate the impact of cost on overall fitness. The higher b, the greater the negative impact of cost on fitness, and systems with lower costs have higher fitness.

[0070] c represents the weighted CO2 emissions. CO2 emissions represent the carbon dioxide emissions generated when distributed power sources are operated. Lower CO2 emissions can reduce negative environmental impacts.

[0071] c moderates the impact of CO2 emissions on overall fitness. The higher c, the greater the negative impact of CO2 emissions on fitness, and systems with lower CO2 emissions have higher fitness.

[0072] Let us look at some usage examples according to one embodiment of the present invention.

[0073] First, when energy efficiency is given top priority, the distributed power optimization device (120) can set the value of a to be large and the values ​​of b and c to be relatively small. For example, the distributed power optimization device (120) can set the value of a to be a = 0.6 and the values ​​of b and c to be b = 0.2 and c = 0.2. In other words, the distributed power optimization device (120) can set the value of a to be larger than the values ​​of b and c.

[0074] Second, when cost reduction is given top priority, the distributed power optimization device (120) can set the b value to be large and the a and c values ​​to be relatively small. For example, the distributed power optimization device (120) can set the b value to b = 0.5 and the a and c values ​​to a = 0.3 and c = 0.2. In other words, the distributed power optimization device (120) can set the b value to be larger than the a and c values.

[0075] Third, when environmental protection is given top priority, the distributed power optimization device (120) can set the c value to be large and the a and b values ​​to be relatively small. For example, the distributed power optimization device (120) can set the c value to b = 0.5 and the a and b values ​​to a = 0.2 and c = 0.3. In other words, the distributed power optimization device (120) can set the c value to be larger than the a and b values.

[0076] Through this, the distributed power generation optimization device (120) can find the optimal distributed power generation combination based on the energy usage pattern and energy demand target of each building based on a genetic algorithm. Here, the distributed power generation optimization device (120) can balance energy efficiency, cost, and CO2 emissions by adjusting at least one of the values ​​a, b, and c. Alternatively, the distributed power generation optimization device (120) can adjust the influence between energy efficiency, cost, and CO2 emissions by adjusting at least one of the values ​​a, b, and c.

[0077] And looking at the selection operation, the distributed power optimization device (120) selects a combination with high fitness and passes it on to the next generation. The distributed power optimization device (120) can select a combination with high fitness using a selection method such as roulette wheel selection or rank selection. Here, the distributed power optimization device (120) can select the combination with the highest fitness or select a predetermined number of combinations in order of increasing fitness.

[0078] Next, regarding the crossover operation, the distributed power optimization device (120) can generate child combinations by crossing selected parent combinations. The distributed power optimization device (120) can cross the parent combinations using a crossover method such as single-point crossover or multi-point crossover.

[0079] And, regarding the mutation operation, the distributed power optimization device (120) can generate new combinations by mutating some genes among the descendant combinations. The distributed power optimization device (120) can mutate some genes among the descendant combinations using a mutation method that randomly changes specific values ​​of the genes.

[0080] And, looking at the termination condition check operation, the distributed power optimization device (120) can check whether a termination condition, such as when a certain number of generations is reached or when the fitness function converges, is satisfied. If the predetermined termination condition is satisfied, the distributed power optimization device (120) can derive an optimal distributed power combination and end the process of deriving the distributed power combination.

[0081] At this time, looking at the iteration operation, if the distributed power optimization device (120) does not satisfy the termination condition, it can return to step S202 (suitability evaluation) and generate the next generation.

[0082] The flowchart illustrated in Figure 3 provides a visual understanding of the process by which a genetic algorithm determines optimal distributed power generation based on a building's energy usage patterns. Each step is designed to achieve a specific goal, and an iterative process can produce an optimal solution.

[0083] Meanwhile, in the genetic algorithm applied to one embodiment of the present invention, mutation is the process of randomly altering some of the genes of an individual (chromosome) to create a new individual. This serves to diversify the search space, increasing the likelihood that the genetic algorithm will find a global optimum without falling into a local optimum.

[0084] Hereinafter, an example scenario according to one embodiment of the present invention will be described.

[0085] First, we assume that the building's distributed power generation mix consists of solar photovoltaics (PV), fuel cells (FC), combined heat and power (CHP), and an energy storage system (ESS). Each gene represents the installed capacity of the corresponding distributed power generation system.

[0086] A genetic entity (Chromosome) can be represented as follows:

[0087] A genetic entity can be expressed in the form [PV, FC, CHP, ESS]. An example genetic entity is expressed as [100, 50, 30, 20]. Here, the genetic entities are PV: 100kW, FC: 50kW, CHP: 30kW, and ESS: 20kWh.

[0088] The mutation process is as follows:

[0089] First, the distributed power optimization device (120) can set a mutation probability. The distributed power optimization device (120) can set a probability (e.g., 5%) of each gene being mutated.

[0090] The distributed power optimization device (120) can perform a mutation process. The distributed power optimization device (120) changes a randomly selected gene. Here, the change can be made by selecting a random value within a specific range or by making a small change to the current value.

[0091] Let's look at an example where the mutation process is applied.

[0092] The initial object can be set as Initial object: [100, 50, 30, 20].

[0093] And mutation processes can occur in the initial organisms. For example, fuel cells (FCs) and energy storage systems (ESSs) can be selected based on their mutation probabilities.

[0094] Next, the distributed power optimization device (120) can randomly change the values ​​of the fuel cell (FC) and ESS.

[0095] And the distributed power optimization device (120) can express the entity after the mutation occurs. For example, the distributed power optimization device (120) can change the value of FC from 50 kW to 55 kW and the value of ESS from 20 kWh to 25 kWh. Here, the entity after the mutation: [100, 55, 30, 25] can be expressed as follows.

[0096] Hereinafter, an example scenario according to one embodiment of the present invention is described in the form of a flowchart.

[0097] First, the initial object can be set as [100, 50, 30, 20]. Here, it can be expressed as PV: 100kW, FC: 50kW, CHP: 30kW, ESS: 20kWh.

[0098] And the distributed power optimization device (120) can cause mutations in the initial entity. For example, the distributed power optimization device (120) can change the FC (50 kW) to 55 kW. In addition, the distributed power optimization device (120) can change the ESS (20 kWh) to 25 kWh.

[0099] Afterwards, the individual after the mutation can be expressed as [100, 55, 30, 25]. Here, PV: 100kW, FC: 55kW, CHP: 30kW, ESS: 25kWh can be expressed as such.

[0100] Meanwhile, the distributed power optimization device (120) according to one embodiment of the present invention can perform a random value selection operation or a small change value application operation using a mutation method.

[0101] First, looking at the random value selection operation, the distributed power optimization device (120) can randomly reset the value of each gene within a specific range. For example, the distributed power optimization device (120) can perform a mutation process by randomly selecting the capacity of the FC between 45 kW and 60 kW.

[0102] Next, looking at the operation of applying a small change value, the distributed power optimization device (120) can apply a small change value by adding or subtracting a small change to the current value. For example, the distributed power optimization device (120) can change the capacity value by randomly adding or subtracting the capacity of the FC within a range of ±10%.

[0103] In this way, mutations in the genetic algorithm applied to one embodiment of the present invention can expand the search space and increase the likelihood of finding an optimal value. The distributed power optimization device (120) can appropriately adjust the frequency and intensity of mutations according to the characteristics of the problem.

[0104] Figure 4 is a configuration diagram of a distributed power optimization device for a building according to one embodiment of the present invention.

[0105] As illustrated in FIG. 4, a distributed power optimization device (120) for a building according to one embodiment of the present invention includes a communication module (210), a memory (220), and a processor (230). However, not all of the illustrated components are essential. The distributed power optimization device (120) may be implemented with more components than the illustrated components, or may be implemented with fewer components.

[0106] Below, the specific configuration and operation of each component of the distributed power optimization device (120) of Fig. 4 are described.

[0107] The communication module (210) communicates with the distributed power applied to the building.

[0108] The memory (220) stores one or more programs related to a method for optimizing distributed power supply of a building.

[0109] The processor (230) executes one or more programs stored in the memory (220). The processor collects energy usage data of the building, identifies energy usage patterns through data analysis of the collected energy usage data, predicts energy demand using a pre-learned demand prediction model, and optimizes the distributed power generation combination applied to the building using a genetic algorithm based on the identified energy usage patterns and predicted energy demand.

[0110] According to embodiments, the processor (230) can optimize a randomly generated initial distributed power source combination for a gene comprising at least one of solar energy, fuel cell, combined heat and power, and energy storage devices using a genetic algorithm.

[0111] According to embodiments, the processor (230) can evaluate the energy efficiency, cost, and CO2 emissions of a distributed power generation combination to calculate a fitness function in a genetic algorithm.

[0112] According to embodiments, the processor (230) can adjust the influence of each of energy efficiency, cost, and CO2 emissions on the suitability of the distributed power source combination by adjusting the respective weights applied to each of the energy efficiency, cost, and CO2 emissions of the distributed power source combination in the genetic algorithm.

[0113] According to embodiments, the processor (230) may set a weight corresponding to a top priority element of a fitness function in the genetic algorithm among energy efficiency, cost, and CO2 emissions of a distributed power source combination in the genetic algorithm to be greater than the remaining weights.

[0114] According to embodiments, the processor (230) may randomly reset the value of each gene within a specific range for some genes among the distributed power combinations in the genetic algorithm or mutate the current value of each gene by adding or subtracting a specific value.

[0115] According to embodiments, the processor (230) can optimize the distributed power combination by repeating the genetic algorithm until a certain number of generations or a fitness function converges.

[0116] Meanwhile, according to one embodiment of the present invention, the various embodiments described above can be implemented as software including instructions stored in a machine-readable storage medium that can be read by a machine (e.g., a computer). The device is a device that can call instructions stored from the storage medium and operate according to the called instructions, and may include an electronic device (e.g., electronic device (A)) according to the disclosed embodiments. When an instruction is executed by a processor, the processor can perform a function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium does not contain a signal and is tangible, and does not distinguish between data being stored semi-permanently or temporarily in the storage medium.

[0117] Furthermore, according to one embodiment of the present invention, the method according to the various embodiments described above may be provided as included in a computer program product. The computer program product may be traded as a commodity between sellers and buyers. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0118] Furthermore, according to one embodiment of the present invention, the various embodiments described above may be implemented in a computer-readable recording medium or a similar device using software, hardware, or a combination thereof. In some cases, the embodiments described herein may be implemented by the processor itself. In a software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

[0119] Meanwhile, computer instructions for performing processing operations of a device according to the various embodiments described above may be stored in a non-transitory computer-readable medium. The computer instructions stored in such a non-transitory computer-readable medium, when executed by a processor of a specific device, cause the specific device to perform processing operations in the device according to the various embodiments described above. A non-transitory computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specific examples of non-transitory computer-readable media may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM.

[0120] In addition, each of the components (e.g., modules or programs) according to the various embodiments described above may be composed of a single or multiple entities, and some of the sub-components described above may be omitted, or other sub-components may be further included in various embodiments. Alternatively or additionally, some components (e.g., modules or programs) may be integrated into a single entity, which may perform the same or similar functions as those performed by each of the respective components prior to integration. Operations performed by modules, programs or other components according to various embodiments may be executed sequentially, in parallel, iteratively or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

[0121] Although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications may be made by a person skilled in the art to which the present disclosure pertains without departing from the gist of the present invention as claimed in the claims. Furthermore, such modifications should not be understood individually from the technical idea or prospect of the present invention.

[0122] [Explanation of symbols]

[0123] 100: Distributed Power Optimization System

[0124] 110: Distributed power source

[0125] 111: Solar power generation

[0126] 112: Fuel cell

[0127] 113: Combined heat and power generation

[0128] 114: ESS

[0129] 120: Distributed Power Optimization Device

[0130] 130: Subordinate

Claims

1. In a distributed power optimization method performed by a distributed power optimization device, A step of collecting energy usage data of a building and identifying energy usage patterns through data analysis of the collected energy usage data; A step of predicting energy demand using a learned demand prediction model; and A method for optimizing distributed power generation in a building, comprising a step of optimizing a distributed power generation combination applied to the building using a genetic algorithm based on the above-mentioned confirmed energy usage pattern and the above-mentioned predicted energy demand.

2. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power generation in a building, wherein a randomly generated initial distributed power generation combination is optimized using the genetic algorithm for genes comprising at least one of solar energy, fuel cells, combined heat and power generation, and energy storage devices.

3. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power generation in a building, which calculates a fitness function in the genetic algorithm by evaluating the energy efficiency, cost, and CO2 emissions of a distributed power generation combination.

4. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power generation in a building, wherein the weights applied to each of the energy efficiency, cost, and CO2 emissions of the distributed power generation combination in the above genetic algorithm are adjusted to adjust the influence of each of the energy efficiency, cost, and CO2 emissions on the suitability of the distributed power generation combination.

5. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power generation in a building, wherein the weight corresponding to the highest priority element of the fitness function in the genetic algorithm among the energy efficiency, cost, and CO2 emissions of the distributed power generation combination in the genetic algorithm is set to be greater than the remaining weights.

6. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power sources in a building, wherein among the distributed power source combinations in the above genetic algorithm, the value of each gene is randomly reset within a specific range for some genes or a specific value is added or subtracted from the current value of each gene to cause mutation.

7. In paragraph 1, The step of optimizing the above distributed power combination is: A method for optimizing distributed power generation in a building, which optimizes the combination of distributed power generation by repeating the above genetic algorithm until a certain number of generations or a fitness function converges.

8. Communication module that communicates with the distributed power applied to the building; memory for storing one or more programs; and comprising a processor for executing one or more of the stored programs; The above processor, Collect energy usage data from buildings, and identify energy usage patterns through data analysis of the collected energy usage data. Predict energy demand using a pre-trained demand forecasting model, A distributed power optimization device for a building that optimizes the distributed power combination applied to the building using a genetic algorithm based on the above-mentioned confirmed energy usage pattern and the above-mentioned predicted energy demand.

9. In paragraph 8, The above processor, A distributed power optimization device for a building, which optimizes a randomly generated initial distributed power combination for a gene composed of at least one of solar power, fuel cell, combined heat and power, and energy storage devices using the genetic algorithm.

10. In paragraph 8, The above processor, A distributed power optimization device for a building that evaluates the energy efficiency, cost, and CO2 emissions of a distributed power combination and calculates a fitness function in the genetic algorithm.

11. In paragraph 8, The above processor, A distributed power optimization device for a building that adjusts the influence of each of energy efficiency, cost, and CO2 emissions on the suitability of a distributed power combination by adjusting the weights applied to each of the energy efficiency, cost, and CO2 emissions of the distributed power combination in the above genetic algorithm.

12. In paragraph 8, The above processor, A distributed power optimization device for a building, which sets the weight corresponding to the highest priority element of the fitness function in the genetic algorithm among the energy efficiency, cost, and CO2 emissions of the distributed power combination in the genetic algorithm to be greater than the remaining weights.

13. In paragraph 8, The above processor, A distributed power optimization device for a building that randomly resets the value of each gene within a specific range among the distributed power combinations in the above genetic algorithm or mutates the current value of each gene by adding or subtracting a specific value.

14. In paragraph 8, The above processor, A distributed power optimization device for a building that optimizes a distributed power combination by repeating the above genetic algorithm until a certain number of generations or a fitness function converges.

Images