Method for designing weather-robust power-to-x system and electronic device therefor

Abstract

Provided are a method for designing a weather-robust power-to-X system and an electronic device therefor. In an embodiment, the electronic device: generates various weather scenarios by using a generative AI model; obtains a local solution, which is a design variable of a power-to-X system for optimizing the performance of the power-to-X system, for each of the various weather scenarios; and obtains a robust solution, which is a design variable of the power-to-X system for enabling the power-to-X system to operate in the various weather scenarios, on the basis of the local solutions of the various weather scenarios.

Description

Method for designing a weather-resistant Power2X system and electronic device for the same

[0001] The present disclosure relates to a method for designing a power-to-X (P2X) system. More specifically, it relates to a method for designing a P2X system capable of operating under various weather conditions.

[0002] Recently, the energy transition aimed at expanding renewable energy supply and achieving carbon neutrality is accelerating globally. P2X technology, which converts electricity generated from renewable sources such as solar, wind, and pumped storage into hydrogen, ammonia, and synthesis gas for storage, transportation, or direct use in chemical processes, is garnering attention.

[0003] However, renewable energies such as solar, wind, and pumped storage are significantly affected by temporal fluctuations in energy resources caused by weather changes, and these fluctuations are emerging as a major challenge for ensuring the stable operation and economic feasibility of P2X systems. In particular, weather conditions that are difficult to predict hourly (wind direction, wind speed, solar radiation, temperature, humidity, etc.) have a significant impact on renewable energy generation and have complex effects on determining the scale of the power conversion process or load distribution.

[0004] Conventionally, P2X systems were designed based on the assumption of statistical average weather. However, designing a P2X system in this manner can result in massive costs or the suspension of operations if the weather differs from the forecast. Therefore, it is necessary to design the P2X system by taking into account the uncertain variability of weather.

[0005] The present disclosure provides a method for designing a P2X system that takes into account the uncertain variability of weather conditions. Furthermore, the present disclosure provides a method for designing a P2X system that can operate in various weather scenarios while optimizing the performance of the P2X system under constraints.

[0006] As a technical means for achieving the technical problems described above, an electronic device for designing a weather-resistant Power2X system according to one aspect of the present invention is provided. The electronic device comprises a memory configured to store one or more instructions and a processor configured to execute the one or more instructions stored in the memory. By executing the one or more instructions, the processor can: generate various weather scenarios using a generative AI model; for each of the various weather scenarios, obtain a local solution, which is a design variable of the Power2X system that optimizes the performance of the Power2X system producing products based on renewable energy under constraints; and, based on the local solutions of the various weather scenarios, obtain a robust solution, which is a design variable of the Power2X system that enables the Power2X system to operate in the various weather scenarios.

[0007] In one embodiment, the processor can generate a weather scenario candidate, which is virtual weather data, from input data based on actual weather data using the generative AI model by executing one or more instructions, and if the result of comparing the weather scenario candidate and the input data satisfies a predetermined condition, the weather scenario candidate can be selected as a weather scenario.

[0008] In one embodiment, the processor may determine whether the comparison result satisfies a predetermined condition based on the overlap rate of the wind rose between the weather scenario candidate and the input data, or whether the comparison result satisfies a predetermined condition based on the similarity of the wind speed Weibull distribution between the weather scenario candidate and the input data by executing one or more instructions.

[0009] In one embodiment, the processor can determine whether the comparison result satisfies a predetermined condition based on the sunrise time or sunset time of the input data and the weather scenario candidate by executing the one or more instructions.

[0010] In one embodiment, the processor generates input data for the generative AI model by performing preprocessing on weather data by executing one or more instructions, the preprocessing includes outlier removal, missing value processing, and data scaling, and the memory may include a database in which the input data is stored.

[0011] In one embodiment, the design variables may include design variables regarding the facility capacity, facility load, power flow, or product flow of the Power2X system.

[0012] In one embodiment, the constraint may include constraints regarding the facility capacity, facility load, power flow, or product flow of the Power2X system.

[0013] In one embodiment, the Power2X system includes an energy storage system comprising storage cells that store power provided by the renewable energy, and the constraints may include that each of the storage cells cannot simultaneously input or output power, that power output of the energy storage system is possible during the operation of the Power2X system, that simultaneous power input or output of the energy storage system is possible, and that power storage in the energy storage system is possible while power is overproduced by the renewable energy.

[0014] In one embodiment, the Power2X system includes a hydrogen storage system comprising an electrolytic cell system that produces hydrogen using electricity and storage tanks that store hydrogen, and the constraints may include that each of the storage tanks cannot simultaneously input or output hydrogen, that hydrogen output from the hydrogen storage system is possible during the operation of the Power2X system, that simultaneous input or output of hydrogen from the hydrogen storage system is possible, and that hydrogen storage in the hydrogen storage system is possible during the overproduction of hydrogen by the electrolytic cell system.

[0015] In one embodiment, the constraint includes a constraint regarding the configuration settings of the Power2X system, and the configuration settings of the Power2X system may include an on / off setting for power supply from the power grid, a setting for the equipment configuration within the budget of the Power2X system, a setting for the limited output power amount of the Power2X system, and a setting for the configuration of the renewable energy system, energy storage system, electrolyzer system, compression system, and hydrogen storage system of the Power2X system.

[0016] In one embodiment, the processor obtains the local solution by executing one or more instructions, thereby optimizing an objective function regarding the performance of the Power2X system under constraints for each of the various weather scenarios, and the objective function can optimize the average cost of the product, the quantity of the product, or the environmental impact of the Power2X system.

[0017] In one embodiment, the objective function includes a main objective function and a sub-objective function, and the processor can obtain the local solution by optimizing the main objective function and the sub-objective function under constraints for each of the various weather scenarios by executing the one or more instructions.

[0018] In one embodiment, the processor can obtain the robust solution within the range of the local solutions by executing the one or more instructions.

[0019] In one embodiment, the processor can generate a comparison result between the local solution of the weather scenario with the largest variance or deviation among the various weather scenarios and the robust solution by executing one or more instructions, or generate a comparison result between the local solution of any weather scenario among the various weather scenarios and the robust solution.

[0020] In one embodiment, the generative AI model may include a diffusion model.

[0021] In one embodiment, the electronic device may further include a user interface configured to provide the user with the various weather scenarios, the constraints, the performance of the Power2X system, the local solution, or the robust solution.

[0022] As a technical means for achieving the aforementioned technical challenges, a method for designing a weather-resistant Power2X system according to one aspect of the present invention is provided. The method may include the steps of: generating various weather scenarios using a generative AI model, and for each of the various weather scenarios, obtaining a local solution which is a design variable of the Power2X system that optimizes the performance of the Power2X system in producing products based on renewable energy under constraints; and obtaining a robust solution which is a design variable of the Power2X system that enables the Power2X system to operate in the various weather scenarios based on the local solutions of the various weather scenarios.

[0023] In one embodiment, the step of generating various weather scenarios may include the step of generating a weather scenario candidate, which is virtual weather data, from input data based on actual weather data using the generative AI model, and the step of selecting the weather scenario candidate as a weather scenario if the result of comparing the weather scenario candidate and the input data satisfies a predetermined condition.

[0024] In one embodiment, the step of selecting the weather scenario candidate as a weather scenario may include the step of determining whether the comparison result satisfies a predetermined condition based on the overlap rate of the wind rose between the weather scenario candidate and the input data.

[0025] In one embodiment, the step of selecting the weather scenario candidate as a weather scenario may include the step of determining whether the comparison result satisfies a predetermined condition based on the similarity between the weather scenario candidate and the Weibull distribution of the wind speed of the input data.

[0026] In one embodiment, the step of selecting the weather scenario candidate as a weather scenario may include the step of determining whether the comparison result satisfies a predetermined condition based on the sunrise time or sunset time of the weather scenario candidate and the input data.

[0027] In one embodiment, the step of generating the various weather scenarios may include the step of generating input data for the generative AI model by performing preprocessing on the weather data.

[0028] In one embodiment, the step of obtaining the local solution includes, for each of the various weather scenarios, obtaining the local solution by optimizing an objective function regarding the performance of the Power2X system under constraints, and the objective function may optimize the average cost of the product, the quantity of the product, or the environmental impact of the Power2X system.

[0029] In one embodiment, the objective function includes a main objective function and a sub-objective function, and the step of obtaining the local solution may include obtaining the local solution by optimizing the main objective function and the sub-objective function under constraints for each of the various weather scenarios.

[0030] In one embodiment, the step of obtaining the robust solution may include the step of obtaining the robust solution within the range of the local solutions.

[0031] In one embodiment, the method may further include the step of generating a comparison result between the local solution of the weather scenario with the largest variance or deviation among the various weather scenarios and the robust solution.

[0032] In one embodiment, the method may further include the step of generating a comparison result between a local solution of any weather scenario among the various weather scenarios and a robust solution.

[0033] As a technical means for achieving the aforementioned technical problems, a computer-readable recording medium is provided having a program recorded thereon for executing any one of the methods described below and the method for designing a weather-resistant Power2X system according to one aspect of the present invention.

[0034] According to the present disclosure, operational stability and economic / environmental benefits of a P2X system can be maximized while responding to the variability in power generation of a renewable energy system caused by weather changes.

[0035] Unlike conventional methods that consider statistical average weather, using generative AI models to consider multiple virtual weather scenarios generated from actual weather data enables the design of P2X systems that account for more realistic weather variability.

[0036] It is possible to design a P2X system by considering both the economic and environmental aspects of the P2X system.

[0037] By determining design variables that enable stable operation under various weather scenarios, the impact of weather uncertainty that may occur in the actual operating environment of the P2X system can be mitigated.

[0038] A P2X system can be designed by considering various renewable energy resources such as solar, wind, hydroelectric, or ocean energy.

[0039] The effects obtainable from the exemplary embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by those skilled in the art from the description of the exemplary embodiments of the present disclosure below. That is, unintended effects resulting from the implementation of the exemplary embodiments of the present disclosure can also be derived by those skilled in the art from the exemplary embodiments of the present disclosure.

[0040] FIGS. 1 to 2c are drawings for illustrating a P2X system according to embodiments.

[0041] FIGS. 3a and 3b show electronic devices according to embodiments.

[0042] FIG. 4 illustrates a design method for a P2X system according to one embodiment.

[0043] Figure 5 shows a diffusion model according to one embodiment.

[0044] FIG. 6 illustrates a method for verifying a weather scenario according to one embodiment.

[0045] Below, with reference to the attached drawings, various embodiments are described in detail to enable those skilled in the art to easily implement the present disclosure. However, since the technical concept of the present disclosure can be modified and implemented in various forms, it is not limited to the embodiments described herein.

[0046] In this specification, when an element is described as "comprising" another element, this means that, unless specifically stated otherwise, it does not exclude other elements in addition to the other elements but may include additional elements. Furthermore, terms such as "module" as described in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software. For example, "module," etc., may be implemented by components such as software components, object-oriented software components, class components, and task components, as well as by processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

[0047] A singular expression may include a plural expression unless the context clearly indicates otherwise.

[0048] FIG. 1 is a drawing for explaining a P2X system according to one embodiment.

[0049] A P2X system is a system that converts power (i.e., P in P2X) produced from renewable energy to produce a product (i.e., X in P2X).

[0050] Renewable energy may be, but is not limited to, solar energy, wind power, hydropower, ocean energy, geothermal energy, or bioenergy.

[0051] The products may be, but are not limited to, gases, liquids, or chemicals. For example, the product of the electrolyzer system of the P2X system may be hydrogen (H₂). Or, the product of the Haber-Bosch system of the P2X system may be ammonia (NH₃). Or, the product of the Fischer-Tropsch system of the P2X system may be a liquid hydrocarbon (e.g., methanol).

[0052] In one embodiment, the P2X system includes a renewable energy system (110), an energy storage system (120, energy storage system; ESS), a balance of plant (130, BOP), an intermediate production system (140, intermediate production system), an intermediate storage system (150, intermediate storage system), an end production system (160, end production system), and an end storage system (170, end storage system). If the P2X system receives power from an external renewable energy system, the P2X system may not include the renewable energy system (110). If the P2X system produces the end product directly without intermediate products, the intermediate production system (140) and the intermediate storage system (150) may be omitted.

[0053] A renewable energy system (110) is a system that produces electricity from renewable energy such as solar energy, wind power, hydropower, ocean energy, geothermal energy, or bioenergy.

[0054] The ESS (120) can store power supplied from the renewable energy system (110). If the amount of power generated by the renewable energy system (110) is greater than a predetermined value or demand, the ESS (120) can perform curtailment to limit excess power output.

[0055] The output power of the ESS (120) can be supplied to other facilities of the P2X system. For example, the output power of the ESS (120) can be supplied to the BOP (130), intermediate production system (140), intermediate storage system (150), final production system (160), and final storage system (170).

[0056] The P2X system can receive power from the power grid. If it does not receive sufficient power from the renewable energy system (110) or if the output power of the ESS (120) is insufficient, the P2X system can receive power from the power grid. The P2X system can control the power supply from the power grid to be on / off. When controlled to On, the P2X system receives power from the power grid, and when controlled to Off, the P2X system does not receive power from the power grid.

[0057] The BOP (130) may include components to support the operation of the P2X system.

[0058] The intermediate production system (140) can produce intermediate products using supplied power. The intermediate products can be stored in the intermediate storage system (150) or provided to the final production system (160).

[0059] The final production system (160) can produce a final product using the supplied power and intermediate products. The final production system (160) can receive intermediate products directly from the intermediate production system (140) or receive intermediate products from the intermediate storage system (150). The final product can be stored in the final storage system (170).

[0060] FIG. 2a is a drawing for explaining a P2X system according to one embodiment. Descriptions that overlap with FIG. 1 are omitted.

[0061] In one embodiment, the P2X system includes a wind power system (211), a solar energy system (212), an ESS (220), a BOP (230), an electrolytic cell system (240), a compression system (250), a hydrogen storage system (260), a nitrogen production system (270), an ammonia production system (280), and an ammonia storage system (290).

[0062] The P2X system can receive power from multiple renewable energy systems. In one embodiment, the P2X system receives power from a wind power system (211) and a solar energy system (212).

[0063] The ESS (220) may include a plurality of storage cells (221), as illustrated in FIG. 2b. The plurality of storage cells (221) may operate in parallel. The ESS (220) may be capable of simultaneous power input and output, but each storage cell (221) may not be capable of simultaneous power input and output. The operation of the plurality of storage cells (221) may be scheduled so that continuous power output of the ESS (220) is possible during the operation of the P2X system.

[0064] The electrolytic cell system (240) can produce hydrogen by using supplied power to separate water into hydrogen and oxygen. The produced hydrogen can be supplied to an ammonia production system (280) or compressed by a compression system (250) and stored in a hydrogen storage system (260). The compression system (250) may include a compressor.

[0065] The electrolytic cell system (240) may be a polymer electrolyte membrane (PEM) electrolytic cell system or an alkaline electrolyser (AEL) system, but is not limited thereto.

[0066] The hydrogen storage system (260) may include a plurality of storage tanks (261), as illustrated in FIG. 2C. The hydrogen storage system (260) may be capable of simultaneous hydrogen input and output, but each storage tank (261) may not be capable of simultaneous hydrogen input and output. The operation of the plurality of storage tanks (261) may be scheduled so that continuous hydrogen output from the hydrogen storage system (260) is possible during the operation of the P2X system.

[0067] The nitrogen production system (270) can separate nitrogen (N2) from the air using supplied power. The separated nitrogen can be supplied to the ammonia production system (280) or stored in a nitrogen storage system (not shown). The nitrogen production system (270) may include an air separation unit (ASU) for nitrogen separation.

[0068] The ammonia production system (280) can produce ammonia by using supplied power to react hydrogen provided from the electrolytic cell system (240) or hydrogen storage system (260) and nitrogen provided from the nitrogen production system (270). The ammonia production system (280) may include a Haber-Bosch system for ammonia production. The produced ammonia may be stored in the ammonia storage system (290).

[0069] To operate a P2X system stably, it must receive a stable power supply from a renewable energy system. If a P2X system is designed by predicting the output of a renewable energy system based on statistical weather data, unexpected output fluctuations may occur in the renewable energy system during actual operation due to weather conditions different from the statistical data, and the P2X system may not be supplied with stable power. To address this problem, embodiments of a method for designing a P2X system while considering the uncertain variability of weather are described.

[0070] FIGS. 3a and 3b show an electronic device (300) according to embodiments.

[0071] The electronic device (300) includes a processor (310) and a memory (320). FIGS. 3a and 3b illustrate components of the electronic device (300) to be described in one embodiment, and the electronic device (300) may further include other components accompanying the implementation of the embodiments.

[0072] Referring to FIG. 3a, the processor (310) typically controls the overall operation of the electronic device (300). The processor (310) can perform basic arithmetic, logic, and input / output operations. The processor (310) can perform the design of the P2X system according to the present invention by executing program code stored in memory (320). For example, the processor (310) may include a processing unit such as a CPU (central processing unit), a GPU (graphics processing unit), or an NPU (neural processing unit).

[0073] The memory (320) is a recording medium readable by the processor (310) and may include a non-perishable mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. The memory (320) may store an operating system and at least one program or application code. The memory (320) may store program code and a database for executing the design of the P2X system according to the present invention.

[0074] The electronic device (300) may further include a communication interface or a user interface, etc., in addition to the processor (310) and memory (320). For example, the communication interface may be configured to perform data communication with another electronic device via wired or wireless communication. For example, the user interface may include an input device such as a keyboard, a mouse, or a touchpad, and an output device such as a speaker or a display device.

[0075] Referring to FIG. 3b, a database (321) may be stored in the memory (320). Additionally, instructions and / or programs for implementing the functions of a data collection module (322), a variable / constraint module (323), a scenario module (324), a local solution module (325), or a robust solution module (326) may be stored in the memory (320).

[0076] The modules (322-326) of the electronic device (300) may actually be configurations implemented by the processor (310) executing a program or instruction stored in memory (320). Accordingly, the operations described below as being performed by the modules (322-326) of the electronic device (300) may actually be performed by the processor (310) of the electronic device (300).

[0077] The processor (310) can perform the design of a P2X system by executing at least one instruction stored in memory (320) and implementing at least one module stored in memory (320). Additionally, the processor (310) can obtain data (e.g., weather data) for performing the design of a P2X system through a communication interface. Additionally, the processor (310) can receive user input for performing the design of a P2X system through a user interface, or provide design data and / or design results of a P2X system to the user.

[0078] FIG. 4 illustrates a design method for a P2X system according to one embodiment.

[0079] A method for designing a P2X system is described by generating weather scenarios using a generative AI model considering the variability of renewable energy caused by uncertain weather changes, obtaining local solutions which are optimal design variables for each weather scenario, and obtaining robust solutions which are design variables robust to various weather scenarios based on the local solutions.

[0080] In step S401, the data collection module (322) collects weather data. For example, the data collection module (322) may download weather data from a website or an external server. The weather data is actual measurement data and may include weather measurements related to renewable energy. For example, the weather data may include wind speed, temperature, solar radiation, etc. The weather data may be data in time units.

[0081] The data collection module (322) can preprocess weather data to generate preprocessed weather data. Preprocessing may include processes for generating input data for a generative AI model. For example, preprocessing may be outlier removal, missing value handling, or data scaling, but is not limited thereto. For example, data scaling may include logarithmic or trigonometric transformations.

[0082] The data collection module (322) can build weather data or preprocessed weather data into a database (321) and store it in memory.

[0083] In step S402, the scenario module (324) generates various weather scenarios using a generative AI model. Here, the weather scenarios are virtual weather data. As the generative AI model generates output in a probabilistic manner, it can generate various virtual weather data from the input data.

[0084] In one embodiment, the input data of the generative AI model may be preprocessed weather data from a database (321). In this case, the scenario module (324) may use the generative AI model to generate various virtual weather data from actual weather data. In another embodiment, the input data of the generative AI model may be noise data.

[0085] The scenario module (324) can generate various weather scenarios from a single input data using a generative AI model. Alternatively, the scenario module (324) can generate various weather scenarios from multiple input data using a generative AI model.

[0086] The scenario module (324) can use a trained generative AI model to generate various weather scenarios. If there is no trained generative AI model, the scenario module (324) can train the generative AI model by using preprocessed weather data from the database (321) as training data.

[0087] A generative AI model can be a diffusion model. Referring to FIG. 5, the diffusion model adds noise (βt) that gradually increases with time steps (t) to the data (X0) to transform the data (X0) into a latent variable (X T A diffusion process (q) that transforms into a latent variable, and a latent variable (X T An inverse process (p) that generates generative data (X') while removing noise from ) θ, backward process), and the probability distribution (p) followed by the learned diffusion model θ (X)) is a latent variable (X T KL divergence (KL(Kullback-Leibler) divergence; D) to approximate the distribution KLIt can be configured as a loss function to minimize the difference between two distributions using ). Data (X0) corresponds to preprocessed weather data, and generative data (X') corresponds to weather scenarios.

[0088] Noise in the diffusion model can enable the generation of weather scenarios that reflect randomness. By generating weather scenarios using the diffusion model, various scenarios that account for weather uncertainty can be produced. By considering diverse weather scenarios with randomness, it is possible to design a P2X system that is robust to various weather conditions.

[0089] The process of generating weather scenarios may include a verification process. More specifically, it may include a process of verifying whether the weather scenarios have a statistical distribution similar to actual weather data. Solar radiation in actual weather data may exist only from sunrise to sunset, and the solar radiation graph of actual weather data may have a camel's hump shape. Wind speed and wind direction in actual weather data can be represented by a Weibull distribution and a wind rose, respectively. The Weibull distribution for wind speed frequency can be expressed by a scale factor (or scale parameter) and a shape factor (or shape parameter). The wind rose for wind direction frequency can represent the prevailing wind direction.

[0090] In one embodiment, the scenario module (324) uses a generative AI model to generate various weather scenario candidates from input data, and among the various weather scenario candidates, a weather scenario candidate that satisfies a predetermined condition based on a comparison result with the input data can be selected as a weather scenario.

[0091] Referring to FIG. 6 for a more detailed explanation, in step S601, the scenario module (324) generates weather scenario candidates from input data using a generative AI model. Here, the input data may be preprocessed weather data based on actual weather data.

[0092] In step S602, the scenario module (324) determines whether the result of comparing the output data of the generative AI model (i.e., weather scenario candidate) with the input data satisfies a predetermined condition. If the predetermined condition is satisfied, the scenario module (324) determines the weather scenario candidate as the weather scenario. If the predetermined condition is not satisfied, the weather scenario candidate is deleted and step S601 is performed.

[0093] In one embodiment, the scenario module (324) can determine whether the comparison result satisfies a predetermined condition based on the overlap rate of the wind rose between the input data and the weather scenario candidate. If the overlap rate of the wind rose between the input data and the weather scenario candidate is greater than a predetermined value, the scenario module (324) can determine the weather scenario candidate as the weather scenario.

[0094] In one embodiment, the scenario module (324) can determine whether the comparison result satisfies a predetermined condition based on the similarity between the input data and the Weibull distribution of wind speed of the weather scenario candidate. If the difference in the scale factor and / or the difference in the shape factor of the Weibull distribution of wind speed of the input data and the weather scenario candidate is smaller than a predetermined value, the scenario module (324) can determine the weather scenario candidate as the weather scenario.

[0095] In one embodiment, the scenario module (324) can determine the weather scenario candidate as a weather scenario if the comparison result based on the overlap rate of the wind rose and the similarity of the wind speed Weibull distribution of the input data and the weather scenario candidate satisfies a predetermined condition. If the overlap rate of the wind rose of the input data and the weather scenario candidate is greater than a predetermined value, and the difference in the scale factor and / or the difference in the shape factor of the wind speed Weibull distribution of the input data and the weather scenario candidate is smaller than a predetermined value, the scenario module (324) can determine the weather scenario candidate as a weather scenario.

[0096] In one embodiment, the scenario module (324) can determine whether the comparison result satisfies a predetermined condition based on the input data and the sunrise time and / or sunset time of the weather scenario candidate. If the sunrise time and / or sunset time match in the input data and the solar radiation data of the weather scenario candidate, the scenario module (324) can determine the weather scenario candidate as the weather scenario.

[0097] Referring again to FIG. 4, in step S403, the variable / constraint module (323) sets the variable / constraint. The variable / constraint module (323) can set design variables, parameters, and constraints for the design of the P2X system. If the variable / constraint is set in advance, step S403 may be omitted, and step S404 may be performed after step S402.

[0098] Design variables may be, but are not limited to, design variables regarding the facility capacity, facility load, power flow, and product flow of the P2X system.

[0099] As examples, but not limited to, design variables regarding facility capacity may include the capacity of a renewable energy system's power generation facility (e.g., solar panel capacity, wind turbine capacity), the capacity of an ESS, the capacity of a BOP, the capacity of an intermediate production system (e.g., electrolytic cell system, nitrogen production system (e.g., ASU)), the capacity of a compression system (e.g., compressor), the capacity of an intermediate storage system (e.g., hydrogen storage system, nitrogen storage system), the capacity of a final production system (e.g., ammonia production system (e.g., Haber-Bosch system)), or the capacity of a final storage system (e.g., ammonia storage system).

[0100] As examples, but not limited to, design variables regarding facility load may include the load of the ESS, the load of the BOP, the load of the intermediate production system, the load of the compression system, or the load of the final production system. Additionally, as examples, but not limited to, design variables regarding facility load may include load fluctuations of the ESS, load fluctuations of the BOP, load fluctuations of the intermediate production system, load fluctuations of the compression system, or load fluctuations of the final production system.

[0101] Power flow is about how power is supplied, distributed, and consumed in a P2X system. As examples, but not limited to, design variables for power flow may include the output power of a renewable energy system (e.g., the amount of power generated by a renewable energy system), the input power of an ESS, the state of charge (SOC) of an ESS, the output power of an ESS, the input power of an intermediate production system, the input power of a compression system, or the input power of a final production system.

[0102] Product flow refers to how products (e.g., intermediate products, final products) are supplied, distributed, and stored in a P2X system. As examples, but not limited to, design variables regarding product flow may include the intermediate product output of an intermediate production system, the intermediate product input / output of a compression system, the intermediate product input / output of an intermediate storage system, the final product input / output of a final production system, or the final product input / output of a final storage system.

[0103] The parameters may be parameters regarding the cost, power consumption, or conversion rate of the P2X system, but are not limited thereto.

[0104] As a non-limited example, cost parameters include the unit price of renewable energy systems (e.g., the unit price of solar power installations (AUD / m²)). 2 It may include the unit price of a wind turbine (AUD / 10MW)), the unit price of an ESS (e.g., AUD / MWh), the unit price of a BOP (e.g., AUD / ton), the unit price of an intermediate production system (e.g., the unit price of an electrolytic cell system (AUD / MW)), the unit price of a compression system (e.g., the unit price of a compressor (AUD / ton)), the unit price of an intermediate storage system (e.g., the unit price of a storage tank (AUD / ton)), or the unit price of a final production system (e.g., the unit price of a Haber-Bosch system (AUD / MW)).

[0105] As examples, but not limited to, parameters regarding power consumption may include the power consumption of the BOP (e.g., MWh), the power consumption of intermediate production systems (e.g., power consumption of the electrolytic system (MWh), power consumption of the ASU (MWh)), the power consumption of compression systems (e.g., power consumption of the compressor (MWh)), or the power consumption of the final production system (e.g., power consumption of the Haber-Bosch system (MWh)).

[0106] The conversion rate relates to how much product is produced by converting electricity or how much final product is produced by converting intermediate products. As examples, but not limited to, parameters regarding the conversion rate may include the conversion rate between electricity and intermediate products (e.g., the conversion rate between electricity and hydrogen, the conversion rate between electricity and nitrogen), the conversion rate between electricity and final products (e.g., the conversion rate between electricity and ammonia), or the conversion rate between intermediate products and final products (e.g., the conversion rate between hydrogen and ammonia).

[0107] Additionally, the parameters may further include parameters regarding the unit price of electricity (e.g., AUD / MWh) or the compression ratio of the compression system (e.g., compressor) for the electricity.

[0108] Constraints may be, but are not limited to, constraints on the facility capacity, facility load, power flow, or product flow of the P2X system.

[0109] As examples not limited to, constraints on facility capacity may include the range of capacity of a renewable energy system's power generation facility, the range of capacity of an ESS, the range of capacity of a BOP, the range of capacity of an intermediate production system, the range of capacity of a compression system, the range of capacity of an intermediate storage system, the range of capacity of a final production system, or the range of capacity of a final storage system.

[0110] As examples, but not limited to, constraints regarding facility load may include the load range of the ESS, the load range of the BOP, the load range of the intermediate production system, the load range of the compression system, or the load range of the final production system. Additionally, as examples, but not limited to, constraints regarding facility load may include the load variation range of the ESS, the load variation range of the BOP, the load variation range of the intermediate production system, the load variation range of the compression system, or the load variation range of the final production system.

[0111] As examples, but not limited to, constraints on power flow may include the range of output power of a renewable energy system (e.g., the range of power generation of a renewable energy system), the range of input / output power of an ESS, the range of SOC of an ESS, the range of charging / discharging time of an ESS, the range of input power of an intermediate production system, the range of input power of a compression system, or the range of input power of a final production system.

[0112] In addition, constraints on power flow may include the fact that the sum of the supply power of the renewable energy system (m1), the discharge power of the ESS (m2), and the supply power of the power grid (m3) is less than or equal to the sum of the charge power of the ESS (m4), the power used by the BOP, intermediate production system, and final production system (m5), and the output-limited power (m6) (m1+m2+m3≤m4+m5+m6).

[0113] In addition, constraints on power flow may include that each storage cell of the ESS cannot simultaneously input or output power, that power output of the ESS is possible during the operation of the P2X system, that simultaneous power input and output of the ESS is possible, or that power storage in the ESS is possible during the surplus power production of the renewable energy system.

[0114] Constraints on power flow may be determined by considering the performance of the equipment, the deterioration of efficiency over time, or maintenance costs. For example, the power generation of a solar panel may be determined by considering the performance of the solar panel, the deterioration of efficiency over time, and maintenance costs. The power generation of a wind turbine may be determined by considering the turbine performance curve, performance degradation due to wake, the deterioration of efficiency over time, and the maintenance costs of the turbine. Constraints on the ESS may be determined by considering the performance degradation due to repeated charging and discharging of the ESS.

[0115] As a non-limiting example, constraints on product flow may include the range of intermediate product output of an intermediate production system, the range of input / output of a compression system, the range of intermediate product input / output of an intermediate storage system, the range of final product input / output of a final production system, or the range of final product input / output of a final storage system.

[0116] In addition, constraints regarding product flow may include that each storage tank of the hydrogen storage system cannot simultaneously input or output hydrogen, that hydrogen output from the hydrogen storage system is possible during the operation of the P2X system, that simultaneous input or output of hydrogen from the hydrogen storage system is possible, that hydrogen can be supplied to the ammonia production system from the hydrogen production system or the hydrogen storage system, or that hydrogen can be stored in the hydrogen storage system during the overproduction of hydrogen in the electrolyzer system.

[0117] Additionally, the constraints include: the sum of the hydrogen production volume (a1) of the electrolytic system and the hydrogen outflow volume (a2) of the hydrogen storage system is less than or equal to the sum of the hydrogen inflow volume (a3) ​​of the hydrogen storage system and the ammonia production volume (a4) of the ammonia production system divided by the conversion rate (a5) between hydrogen and ammonia (a1+a2≤a3+a4 / a5); the hydrogen production volume (b1) of the electrolytic system is less than or equal to the product of the power consumption volume (b2) of the electrolytic system and the conversion rate between power and hydrogen (b3) (b1≤b2*b3); the nitrogen production volume (c1) of the nitrogen production system is less than or equal to the product of the power consumption volume (c2) of the nitrogen production system and the conversion rate between power and nitrogen (c3) (c1≤c2*c3); or the ammonia production volume (d1) of the ammonia production system is less than or equal to the product of the power consumption volume (d2) of the ammonia production system and the conversion rate between power and ammonia (d3) (d1≤d2*d3). It is possible.

[0118] Additionally, the variable / constraint module (323) can configure the P2X system. As examples, but not limited to, the variable / constraint module (323) can configure the on / off state of power supply from the power grid, configure the facility within the budget, configure the range of the output limiting power amount, configure the renewable energy system (e.g., set the ratio of solar energy system to wind system), configure the electrolyzer system (e.g., set the ratio of PEM or AEL), configure the ESS and hydrogen storage system (e.g., set the ratio of ESS to hydrogen storage system), or configure the compressor system and hydrogen storage system (e.g., set the performance of the compressor and the capacity of the hydrogen storage system considering the trade-off). The configuration of the P2X system can be used as a constraint.

[0119] In step S404, the local solution module (325) obtains a local solution for each of the various weather scenarios. The local solution may be a design variable that optimizes the performance of a P2X system that produces products based on renewable energy while satisfying constraints set under the weather scenario.

[0120] The performance of the P2X system can be expressed in terms of economic and / or environmental performance. In terms of economic performance, the objective function of optimization may be the average cost of the product (LCOX (levelized cost of X, e.g., LCOA (levelized cost of ammonia)), LCOH (levelized cost of hydrogen)) or the quantity of the product. For example, the local solution module (325) may obtain a local solution by finding design variables that minimize LCOX under constraints for each of the various weather scenarios. As another example, the local solution module (325) may obtain a local solution by finding design variables that maximize the quantity of the product under constraints for each of the various weather scenarios. In terms of environmental performance, the objective function of optimization may be environmental impact. Environmental impact may be defined based on heat balance, material balance, gas emissions (e.g., carbon emissions), or environmental impact indicators. Designing a P2X system that minimizes environmental impact can enable the operation of an environmentally friendly P2X system. For example, the local solution module (325) can obtain a local solution by finding design variables that minimize environmental impact (e.g., minimize carbon emissions) under constraints for each of the various weather scenarios.

[0121] Multiple objective functions representing the performance of the P2X system may be used for optimization. For example, the primary objective function may be LCOX, and the secondary objective function may be the quantity of the final product or environmental impact. The local solution module (325) may optimize the primary objective function first and then optimize the secondary objective function, optimize the primary objective function with the secondary objective function as a constraint, or perform optimization by considering the trade-off between the primary objective function and the secondary objective function. For example, the local solution module (325) may obtain a local solution by finding design variables that minimize environmental impact (e.g., minimize carbon emissions) while minimizing LCOX under constraints for each of various weather scenarios. As another example, the local solution module (325) may obtain a local solution by finding design variables that maximize the quantity of the final product while minimizing LCOX under constraints for each of various weather scenarios.

[0122] The local solution module (325) may use various optimization algorithms. For example, multi-objective optimization algorithms, Pareto-optimal solutions, or mathematical model-based algorithms (e.g., linear programming (LP) / nonlinear programming (NLP) / mixed integer programming (MIP)) may be used, but are not limited thereto.

[0123] In step S405, the robust solution module (326) obtains a robust solution based on local solutions. The robust solution may be a design variable of the P2X system that enables the P2X system to operate robustly in various weather scenarios.

[0124] The robust solution module (326) can synthesize local solutions to determine a robust solution, which is a design variable that enables the P2X system to operate stably in various weather scenarios. The robust solution module (326) can use various robust optimization algorithms to determine the robust solution. The robust solution may not be the optimal solution for each weather scenario, but it may be a solution that guarantees a certain level of performance of the P2X system in various weather scenarios.

[0125] Since the robust solution is based on local solutions for various weather scenarios, a P2X system equipped with the robust solution can operate reliably under diverse weather conditions. Furthermore, since the robust solution is based on local solutions that optimize the performance of the P2X system, the performance (i.e., economic and / or environmental performance) of the P2X system equipped with the robust solution can be guaranteed.

[0126] In one embodiment, the robust solution module (326) can obtain a robust solution within the range of local solutions. In other words, the robust solution module (326) can determine a robust solution to be included within the range formed by the local solutions. For example, if the local solutions are 2.2, 2.6, and 2.8, the robust solution can be determined within the range of local solutions, which is 2.2 to 2.8.

[0127] In one embodiment, the robust solution module (326) may obtain a robust solution from the average or weighted average of local solutions. For example, if the local solutions are 2.2, 2.6, and 2.8 and their respective weights are 1.2, 1, and 1, the weighted average of approximately 2.5 may be determined as the robust solution.

[0128] In one embodiment, the robust solution module (326) can determine a robust solution so that the performance of the P2X system can be maintained even in the worst weather scenario among various weather scenarios. The worst weather scenario may be the weather scenario with the largest variance or deviation among various weather scenarios. For example, if the P2X system can be operated in other weather scenarios with a local solution for the worst weather scenario, the robust solution module (326) may determine the local solution for the worst weather scenario as the robust solution. As another example, the robust solution module (326) may obtain the robust solution from the weighted average of the local solutions by assigning a high weight to the local solution for the worst weather scenario.

[0129] The process of determining a robust solution may include a verification process. More specifically, it may include a process of verifying whether a P2X system having a robust solution as a design variable can operate robustly under various weather scenarios. The robust solution module (326) can determine whether the performance of the P2X system having the robust solution under various weather scenarios satisfies predetermined conditions. For example, the robust solution module (326) can determine whether the LCOX of the P2X system, the amount of product, or environmental impact satisfies predetermined values. If the predetermined conditions are satisfied, the robust solution module (326) can finalize the robust solution. If the predetermined conditions are not satisfied, the robust solution module (326) can obtain the robust solution again through a modification process, such as changing the weight of the weighted average.

[0130] The robust solution module (326) can generate a comparison result between the local solution and the robust solution of the weather scenario with the largest variance or deviation among various weather scenarios. Additionally, the robust solution module (326) can generate a comparison result between the local solution and the robust solution of any weather scenario among various weather scenarios. The comparison result may include numerical comparison data between the local solution and the robust solution and / or performance comparison data of the P2X system between the local solution and the robust solution. The robust solution module (326) can store the comparison result in memory (320) or provide it to the user through a user interface.

[0131] Additionally, the processor (310) may provide the design process of the P2X system to the user through a user interface (e.g., a display device). For example, the processor (310) may provide the user through a user interface the weather data and preprocessed weather data of step S401, various weather scenarios of step S402, the verification process of weather scenario candidates, design variables, parameters, and constraints of step S403, the local solution and performance of the P2X system (i.e., objective function) of step S404, and the robust solution of step S405.

[0132] The various embodiments described above may be implemented in the form of a computer program that can be executed on a computer through various components, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may continuously store the computer-executable program or temporarily store it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system but may also exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0133] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0134] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

1. In an electronic device for designing a weather-resistant Power2X system, Memory configured to store one or more instructions; and It includes a processor configured to execute one or more instructions stored in the memory, and The above processor executes one or more of the above instructions: Generate various weather scenarios using generative AI models, and For each of the various weather scenarios mentioned above, obtain a local solution, which is a design variable of the Power2X system, that optimizes the performance of the Power2X system producing products based on renewable energy under constraints, and An electronic device that obtains a robust solution, which is a design variable of the Power2X system, enabling the Power2X system to operate in the various weather scenarios based on local solutions of the various weather scenarios.

2. In Paragraph 1, The above processor executes the above one or more instructions, Using the above generative AI model, weather scenario candidates, which are virtual weather data, are generated from input data based on actual weather data, and An electronic device that selects the weather scenario candidate as a weather scenario when the result of comparing the weather scenario candidate and the input data satisfies a predetermined condition.

3. In Paragraph 2, The above processor executes the above one or more instructions, An electronic device that determines whether the comparison result satisfies a predetermined condition based on the overlap rate of the wind rose between the weather scenario candidate and the input data, or determines whether the comparison result satisfies a predetermined condition based on the similarity of the Weibull distribution of the wind speed between the weather scenario candidate and the input data.

4. In Paragraph 2, The above processor executes the above one or more instructions, An electronic device that determines whether the comparison result satisfies a predetermined condition based on the above-mentioned weather scenario candidate and the above-mentioned sunrise or sunset time of the above-mentioned input data.

5. In Paragraph 1, The above processor executes the above one or more instructions, Input data for the above generative AI model is generated by performing preprocessing on weather data, and The above preprocessing includes outlier removal, missing value processing, and data scaling, and The above memory is an electronic device comprising a database in which the above input data is stored.

6. In Paragraph 1, The above design variables include design variables regarding the facility capacity, facility load, power flow, or product flow of the Power2X system, in an electronic device.

7. In Paragraph 1, The above constraints include constraints regarding the facility capacity, facility load, power flow, or product flow of the Power2X system, in an electronic device.

8. In Paragraph 1, The above Power2X system includes an energy storage system comprising storage cells that store power provided by the renewable energy, and The above constraints include that each of the storage cells cannot simultaneously input / output power, that power output of the energy storage system is possible during the operation of the Power2X system, that simultaneous power input / output of the energy storage system is possible, and that power storage of the energy storage system is possible while power is overproduced by the renewable energy.

9. In Paragraph 1, The above Power2X system includes an electrolyzer system that produces hydrogen using electricity and a hydrogen storage system that includes storage tanks for storing hydrogen, and The above constraints include that each of the storage tanks cannot simultaneously input or output hydrogen, that hydrogen output from the hydrogen storage system is possible during the operation of the Power2X system, that simultaneous input or output of hydrogen from the hydrogen storage system is possible, and that hydrogen storage in the hydrogen storage system is possible during the overproduction of hydrogen from the electrolytic cell system.

10. In Paragraph 1, The above constraints include constraints regarding the configuration settings of the Power2X system, and An electronic device comprising a configuration setting of the above Power2X system, the on / off setting of power supply from the power grid, the configuration setting of the equipment within the budget of the above Power2X system, the setting of the output limited power amount of the above Power2X system, and the configuration setting of the renewable energy system, energy storage system, electrolyzer system, compression system, and hydrogen storage system of the above Power2X system.

11. In Paragraph 1, The above processor executes the above one or more instructions, For each of the various weather scenarios mentioned above, the local solution is obtained by optimizing the objective function regarding the performance of the Power2X system under constraints, and The above objective function is an electronic device that optimizes the average cost of the product, the quantity of the product, or the environmental impact of the Power2X system.

12. In Paragraph 11, The above objective function includes a primary objective function and a secondary objective function, and The above processor executes the above one or more instructions, An electronic device that obtains the local solution by optimizing the main objective function and the sub-objective function under constraints for each of the various weather scenarios above.

13. In Paragraph 1, The above processor executes the above one or more instructions, An electronic device that obtains the robust solution within the scope of the above local solutions.

14. In Paragraph 1, The above processor executes the above one or more instructions, An electronic device that generates a comparison result between a local solution of the weather scenario with the largest variance or deviation among the various weather scenarios and the robust solution, or generates a comparison result between a local solution of any weather scenario among the various weather scenarios and the robust solution.

15. In Paragraph 1, The above generative AI model is an electronic device including a diffusion model.

16. In Paragraph 1, An electronic device further comprising a user interface configured to provide the user with the various weather scenarios, the constraints, the performance of the Power2X system, the local solution, or the robust solution.

17. A method for designing a weather-resistant Power2X system, The above method is performed by a processor, and A step of generating various weather scenarios using a generative AI model; For each of the various weather scenarios above, a step of obtaining a local solution, which is a design variable of the Power2X system, that optimizes the performance of the Power2X system producing products based on renewable energy under constraints; and A method comprising the step of obtaining a robust solution, which is a design variable of the Power2X system, that enables the Power2X system to operate in the various weather scenarios, based on local solutions of the various weather scenarios.

18. A computer-readable recording medium storing a program for executing the method of paragraph 17 on a computer.

Images