Low-carbon energy system design and planning method and device based on source-grid-load-storage hydrogen chemical industry

Abstract

This invention discloses a method and apparatus for designing and planning a low-carbon energy system based on a source-grid-load-storage hydrogen chemical industry. The method includes: acquiring user natural language information; constructing a large-scale low-carbon energy system planning model; the large-scale low-carbon energy system planning model including a large language model and a planning module; inputting user natural language information into the large language model to identify user intent, and invoking the planning module based on the identified user intent; converting user natural language information into input data in a preset format and inputting it into the planning module, and outputting a planning report through optimization and solution by the planning module; and displaying the planning results corresponding to the planning report through the large language model. This invention establishes the first intelligent agent for energy knowledge processing and data parsing, ultimately enabling the large language model to autonomously plan and design based on user natural language questions, providing users with a user-friendly interactive experience and high-quality design and planning reports.

Description

Technical Field

[0001] This invention relates to the field of energy large-scale modeling technology, and in particular to a method and apparatus for designing and planning low-carbon energy systems based on source-grid-load-storage-chemical processes. Background Technology

[0002] In the field of large-scale energy models, existing models mainly focus on implementing knowledge-based question-and-answer functions and are primarily concentrated on a single area of ​​traditional power production / transmission. They lack deeply coupled models encompassing multiple energy sources, energy storage forms, and application scenarios in the low-carbon field. Current intelligent agent implementations are mostly based on open-source frameworks, such as LangChain, with numerous tools available in the community. However, tools related to low-carbon energy system planning and design are lacking, requiring customized development. While existing low-carbon energy system design and planning tools can cover conventional planning scenarios, they struggle to meet the specific needs of current low-carbon energy systems. Furthermore, they lack open-source availability and the ability to connect with large-scale models. Therefore, the independent development of low-carbon energy system design and planning tools is necessary.

[0003] The underlying principles of large-scale models prevent them from performing complex mathematical calculations. However, design and planning involve complex optimization algorithms that cannot be implemented solely by the large-scale model. Therefore, accurate invocation of the design and planning module by the large-scale model is required to achieve this functionality. Currently, open-source framework-based intelligent agent toolkits lack tools related to low-carbon energy system planning and design, making it impossible to integrate large-scale models with design and planning.

[0004] Current low-carbon energy system planning tools have the following shortcomings: First, the models are not comprehensive or detailed enough, lacking characterization of chemical products such as methanol and ammonia, as well as the variable operating conditions of some power generation technologies; second, the models lack built-in databases, and some current planning tools still require manual input of some data; third, current planning tools generally lack the ability to connect with large models, and some current tools have high barriers to entry, requiring certain professional knowledge to use; fourth, current tools are mostly simulation-based, lacking the ability to provide optimal scheduling solutions in real time, and the current planning tools lack multi-timescale scheduling, and lack planning from multiple time perspectives such as day-ahead, mid-day, and real-time. Summary of the Invention

[0005] The present invention aims to at least partially solve one of the technical problems in the related art.

[0006] To this end, this invention proposes a low-carbon energy system design and planning method based on source-grid-load-storage hydrogen chemical engineering. It combines a large language model and planning and design tools into an intelligent agent, enabling users to complete the planning and design of low-carbon energy systems with low barriers to entry and using natural language as the interaction form.

[0007] Another objective of this invention is to propose a design and planning device for a low-carbon energy system based on source-grid-load-storage hydrogen chemical engineering.

[0008] To achieve the above objectives, this invention proposes a low-carbon energy system design and planning method based on source-grid-load hydrogen storage chemical engineering, comprising:

[0009] Obtain user natural language information;

[0010] A large-scale planning model for a low-carbon energy system is constructed; the large-scale planning model for a low-carbon energy system includes a large language model and a planning module; wherein, the planning module includes a database, a model library, a design optimization module, and an operation optimization module;

[0011] The user's natural language information is input into the large language model to identify the user's intent, and the planning module is invoked based on the identified user intent.

[0012] The user's natural language information is transformed into input parameters for the planning module through a large language model and then input into the design optimization module through a preset interface. The design optimization module has a built-in database and model library. An optimization problem is constructed in the design optimization module. Based on the built-in model library and database data, the optimal planning is carried out under various boundary conditions in a way that minimizes the total cost. After calculation by the optimization algorithm, the optimal design scheme of the system and various performance indicators of the system are generated.

[0013] Based on the optimal system design scheme and various system performance indicators, the system capacity is reconfigured to obtain a custom capacity configuration, and custom topology relationships are designed for various energy utilization modules in the model library to obtain custom topology relationships. Based on the custom capacity configuration and custom topology relationships, and combined with the model library and database, an optimization problem is constructed. The minimum daily operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. Optimization is performed at multiple time scales to output the optimization solution results.

[0014] The low-carbon energy system design and planning method based on source-grid-load-storage-chemical engineering in this invention embodiment may also have the following additional technical features:

[0015] In one embodiment of the present invention, the user natural language information includes at least the geographical location of the energy system, latitude and longitude, type of power generating unit, usage status of energy storage modules, electricity demand, and carbon emission-related constraints; the database includes various types of data such as equipment data, meteorological data, grid connection policies, load data, and other data; the model library includes various types of data such as source-side models, grid-side models, load-side models, storage-side models, hydrogen-side data, and chemical data.

[0016] In one embodiment of the present invention, the optimization variables of the optimization algorithm include system design variables, namely the installed capacity of various energy technologies, and system operation variables, namely the operation strategies of each unit; the objective function of the optimization algorithm is to minimize the annualized system cost; the constraint equations of the optimization algorithm include multiple of the following: installed capacity constraints, total system carbon emission constraints, unit operation constraints, unit operation status calculation equations, system power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

[0017] In one embodiment of the present invention, the operation optimization module further includes a front-end interface.

[0018] Users can input custom capacity configurations and custom topology relationships through the front-end interface, and generate system reports based on the obtained optimization results.

[0019] In one embodiment of the present invention, the optimization solution result includes:

[0020] This includes various factors such as system balance, system operating costs, load shedding, energy storage, and renewable energy consumption.

[0021] To achieve the above objectives, another aspect of the present invention proposes a low-carbon energy system design and planning device based on source-grid-load hydrogen storage chemical engineering, comprising:

[0022] The user data acquisition module is used to acquire users' natural language information;

[0023] The system model building module is used to construct a large-scale low-carbon energy system planning model; the large-scale low-carbon energy system planning model includes a large language model and a planning module; wherein, the planning module includes a database, a model library, a design optimization module, and an operation optimization module;

[0024] The model invocation module is used to input the user's natural language information into the large language model to identify the user's intent, and then invoke the planning module based on the identified user intent.

[0025] The design optimization calculation module uses a large language model to transform the user's natural language information into input parameters for the planning module, and inputs them into the design optimization module through a preset interface. The design optimization module has a built-in database and model library. It constructs an optimization problem in the design optimization module, and performs optimal planning under various boundary conditions in a way that minimizes the total cost based on the built-in model library and database data. After calculation by the optimization algorithm, it generates the optimal design scheme of the system and various performance indicators of the system.

[0026] The optimization output module is used to reconfigure the system capacity to obtain a custom capacity configuration based on the optimal system design scheme and various system performance indicators, and to design custom topology relationships for various energy utilization modules in the model library to obtain custom topology relationships. Based on the custom capacity configuration and custom topology relationships, and in conjunction with the model library and database, an optimization problem is constructed. The minimum daily operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is then performed at multiple time scales to output the optimization solution results.

[0027] This invention relates to a method and apparatus for designing and planning a low-carbon energy system based on a source-grid-load-storage-chemical process. It utilizes a solution based on a low-carbon energy data resource library and optimization algorithm library to explore a development technology roadmap for a low-carbon system design platform encompassing energy, power, and chemical integration. The invention constructs the first planning and design platform that meets the multi-energy heterogeneous coupling requirements of low-carbon energy systems. It also employs large language model technology to train the first professional large-scale model in the low-carbon energy field and establishes the first intelligent agent for energy knowledge processing and data parsing. Ultimately, the large language model can autonomously plan and design based on user natural language queries, providing users with a user-friendly interactive experience and high-quality design and planning reports.

[0028] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0029] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0030] Figure 1 This is a flowchart of a low-carbon energy system design and planning method based on source-grid-load-storage hydrogen chemical engineering according to an embodiment of the present invention;

[0031] Figure 2 This is a JSON-formatted algorithm flowchart according to an embodiment of the present invention;

[0032] Figure 3 This is a block diagram of a low-carbon energy system planning intelligent agent according to an embodiment of the present invention;

[0033] Figure 4 This is a logic diagram of a low-carbon energy system planning module according to an embodiment of the present invention;

[0034] Figure 5 This is a schematic diagram of a low-carbon energy system design module according to an embodiment of the present invention;

[0035] Figure 6 This is a schematic diagram of the low-carbon energy system operation module according to an embodiment of the present invention;

[0036] Figure 7 This is a structural diagram of a low-carbon energy system design and planning device based on source-grid-load hydrogen storage chemical engineering according to an embodiment of the present invention. Detailed Implementation

[0037] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0038] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0039] The following description, with reference to the accompanying drawings, describes a low-carbon energy system design and planning method and apparatus based on source-grid-load-storage hydrogen chemical engineering, according to embodiments of the present invention.

[0040] Figure 1 This is a flowchart of a low-carbon energy system design and planning method based on source-grid-load-storage hydrogen chemical engineering according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0041] S1, obtain user natural language information;

[0042] S2, Construct a large-scale low-carbon energy system planning model; the large-scale low-carbon energy system planning model includes a large language model and a planning module; wherein, the planning module includes a database, a model library, a design optimization module and an operation optimization module;

[0043] S3 inputs the user's natural language information into the large language model to identify the user's intent, and calls the planning module based on the identified user intent.

[0044] S4, through a large language model, transforms the content of the user's natural language information into input parameters for the planning module, and inputs them into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, constructs an optimization problem in the design optimization module, and performs optimal planning under various boundary conditions in a way that minimizes the total cost based on the built-in model library and database data, and generates the optimal design scheme of the system and various performance indicators of the system after calculation by the optimization algorithm;

[0045] S5: Based on the optimal system design scheme and various system performance indicators, the system capacity is reconfigured to obtain a custom capacity configuration, and custom topology relationships are designed for various energy utilization modules in the model library to obtain custom topology relationships. Based on the custom capacity configuration and custom topology relationships, and combined with the model library and database, an optimization problem is constructed. The minimum daily operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is solved at multiple time scales to output the optimization solution results.

[0046] In one embodiment of the present invention, the user can interact with the intelligent agent in the form of natural language information, and the large language model automatically selects to directly answer the user's questions by recognizing the user's intent.

[0047] Specifically, the large language model analyzes the user's question or description to understand its meaning and context. It determines the type of information the user wants to obtain or the task they need to perform. If necessary, it utilizes search functionality to retrieve the latest information or data. Based on the understood content and retrieved information, it constructs an accurate, relevant, and helpful answer. The generated answer is then presented to the user in natural language.

[0048] In one embodiment of the present invention, the present invention can input user natural language information into a large language model to identify user intent, and then invoke a planning module based on the identified user intent. If the user chooses to invoke the planning module, the large language model will generate an invocation command in JSON format, as shown in the example below. Figure 2 As shown in the diagram. "action" corresponds to the tool name, and "action_input" corresponds to the tool's input parameter name and corresponding value. Latitude and longitude, power unit type, energy storage module usage status, power demand, and carbon emission constraints are converted into input data in a preset format and transmitted to the low-carbon system design and planning tool. If the user does not input the required parameters for the design and planning tool, the agent will prompt the user to add the corresponding parameters. If the parameters meet the requirements, the agent calls the design and planning module with the user's input parameters. The design and planning module returns a planning report, and the large language model summarizes and refines the planning report before returning the planning results to the user. The overall structure is as follows: Figure 3 As shown.

[0049] Compared to existing energy system planning and design products, which often rely on graphical interfaces for dragging and dropping parameters or requiring users to fill out forms before running the program, this invention presents a significant learning curve. This invention combines a large language model with planning and design tools into an intelligent agent, enabling users to easily complete low-carbon energy system planning and design using natural language as the interaction method.

[0050] In one embodiment of the present invention, it is necessary to construct a large-scale low-carbon energy system planning model; the large-scale low-carbon energy system planning model includes a large language model and a planning module.

[0051] The main components and logic of the planning module in this embodiment of the invention are as follows: Figure 4 As shown, it mainly consists of four parts: first, the database, as shown in the attached diagram. Figure 3 As shown, the system primarily includes equipment data, meteorological data, grid connection policies, load data, and other data; secondly, a model library, mainly containing source-side models, grid-side models, load-side models, storage-side models, hydrogen data, and chemical data; and thirdly, a design optimization module, the main principles of which are shown in the attached diagram. Figure 5 As shown; fourth is the operation optimization module, the main principle of which is as follows: Figure 6 As shown.

[0052] Specifically, this invention converts user natural language information into input data in a preset format and inputs it into the planning module. The planning module then optimizes and solves the problem to output a planning report. The main operating logic is as follows:

[0053] The large model transforms the geographical location of the energy system, the type of power generation unit, the power demand, and carbon emission-related constraints contained in the user's natural language into input parameters for the planning module, which are then input into the design optimization module through the interface of the design module.

[0054] The design optimization module has a built-in database and model library. It accesses the data in the database and model library and generates a capacity configuration scheme through a specific optimization algorithm.

[0055] After configuring the capacity plan, users can customize the connection and design in the front-end interface of the operation optimization module. The final scheduling plan is generated after optimization by the operation optimization module.

[0056] The schematic diagram of the design optimization module of this invention is attached. Figure 5 As shown, its input data consists of the generator set's fixed capacity, latitude and longitude, and the main components of the system, which are converted from user-input text into input parameters for the design optimization module.

[0057] For example, the design optimization module of the present invention has a built-in database and model library, accesses data in the database and model library, and generates a capacity configuration scheme through a specific optimization algorithm, which may specifically include:

[0058] The optimization module constructs an optimization problem, combines various built-in model libraries and database data, and performs optimal planning under various boundary conditions in a way that minimizes the total cost. After calculation by the optimization algorithm, the optimal design scheme of the system and various performance indicators of the system are generated.

[0059] It is understandable that the optimization variables of the optimization algorithm for the design optimization module in a low-carbon energy system include system design variables, namely the installed capacity of various energy technologies, and system operation variables, namely the operation strategies of each unit. The objective function of the optimization algorithm is to minimize the annualized cost of the system. The constraint equations of the optimization algorithm include multiple ones, such as installed capacity constraints, total carbon emission constraints of the system, unit operation constraints, unit operation state calculation equations, system power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

[0060] Specifically, taking an integrated photovoltaic-storage-charging system as an example, the input parameters include the photovoltaic output curve, the charging demand curve, and technical and economic parameters such as the grid connection price and energy storage cost. The planning objective is to maximize the system's annualized profit.

[0061] maxR = R net +R char -C buy -C inv

[0062] R represents the system's annualized profit, which includes: the system's annual grid-connected revenue R net The system's annual electricity sales revenue R char The system's annual electricity purchase cost C buy Annualized investment cost of energy storage C inv .

[0063] The constraints include:

[0064] (1) Capacity constraint:

[0065] 0.2 ≤ SOC(t) ≤ 0.9

[0066] This indicates that energy storage batteries should operate within a certain state of charge range.

[0067] (2) Capacity recovery constraint:

[0068] SOC start =SOC end

[0069] This indicates that the energy storage battery returns to its initial state of charge after one operating cycle.

[0070] (3) Equipment status constraints:

[0071] x cha (t)+x dis (t)=1

[0072] This indicates that at time t, the energy storage battery cannot be charged or discharged simultaneously.

[0073] (4) Supply and demand balance constraints:

[0074] Ppv (t)=P pv2grid (t)+P pv2bat (t)+P pv2load (t)

[0075] This indicates that at time t, the photovoltaic output has three destinations: external power grid transmission, battery energy storage, and load consumption.

[0076] P load (t)=P pv2load (t)+P bat2load (t)+P grid2load (t)

[0077] This indicates that at time t, the load supply is met by three parts: photovoltaic power output, battery energy storage, and grid power purchase.

[0078] Ultimately, the output of the design optimization module is the system's annualized revenue, battery capacity configuration strategy, and system operation strategy.

[0079] Furthermore, the schematic diagram of the operation optimization module is attached. Figure 6 As shown, it mainly consists of three components: a user-interactive front-end, a model library database, and optimization algorithms.

[0080] Specifically, based on the capacity configuration plan, the user customizes the connection and design in the front-end interface of the operation optimization module. After optimization by the operation optimization module, the final scheduling plan is generated, which may include:

[0081] Based on the results calculated by the design optimization module, namely the optimal system design scheme and various system performance indicators, users can independently reconfigure the capacity and design custom topology relationships for various energy utilization modules.

[0082] Based on custom capacity configuration and custom topology, and combined with model library and database, an optimization problem is constructed. The daily minimum operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is then performed at multiple time scales to output the optimization results.

[0083] Understandably, the operation optimization module constructs optimization problems based on various capacity configurations and topology relationships input by the user, combined with the model library and database. It then performs optimization across multiple time scales, including rolling optimization from the perspectives of day-ahead, intraday, and real-time, guiding actual production. The operation optimization module ultimately sends the optimization results to the front end for user feedback. A system report can be generated through the front-end interface based on the obtained optimization results.

[0084] It is known that the optimization results generated by the optimization module include multiple aspects such as system balance, system operating cost, load shedding, energy storage, and renewable energy consumption.

[0085] For example, taking a "photovoltaic-storage-charging integrated system" as an example, the operation optimization module first predicts the solar irradiance and load demand for the next day at a resolution of 60 minutes, and uses this as input parameters to obtain the system operation strategy for the next day, i.e., intraday optimization. In intraday rolling optimization, the day-ahead optimization results are corrected at a resolution of 15 minutes and a prediction time domain of 4 hours, such as modifying the distribution of photovoltaic power output and the operation curve of battery storage. In real-time optimization, the output of fast-acting units is adjusted at a resolution of 1 minute and a prediction time domain of 5 minutes to compensate for fluctuations in load demand and renewable energy generation.

[0086] In summary, the beneficial effects of the present invention are as follows:

[0087] Given the current focus of smart energy platforms on energy-electricity-heat / steam, this study delves into the independent optimization of energy, electricity, and chemical processes in the low-carbon energy sector, as well as the high barriers to entry for traditional planning and design platforms. It researches and develops innovative technical methods, including establishing a data resource and optimization algorithm library, and developing the first low-carbon system planning and design module for collaborative optimization of energy, electricity, and materials. This aims to create an intelligent agent in the low-carbon energy field, with a large model as the decision-making center and design and planning modules as the tool library. The goal is to address key technical challenges in smart low-carbon energy system planning and design platforms and ultimately build a platform that uses natural language for interaction.

[0088] According to the present invention, the low-carbon energy system design and planning method based on source-grid-load-storage hydrogen chemical industry adopts large language model technology to train the first professional large model in the field of low-carbon energy, and at the same time establishes the first intelligent agent for energy knowledge processing and data analysis. Finally, the large language model can autonomously plan and design functions based on the user's natural language questions, providing the user with a friendly interactive experience and high-quality design and planning reports.

[0089] To achieve the above embodiments, such as Figure 7 As shown, this embodiment also provides a low-carbon energy system design and planning device 10 based on source-grid-load hydrogen storage and chemical engineering, including:

[0090] User data acquisition module 100 is used to acquire user natural language information;

[0091] The system model building module 200 is used to build a large-scale low-carbon energy system planning model; the large-scale low-carbon energy system planning model includes a large language model and a planning module; wherein, the planning module includes a database, a model library, a design optimization module and an operation optimization module;

[0092] The model invocation module 300 is used to input user natural language information into the large language model to identify user intent, and then invoke the planning module based on the identified user intent.

[0093] The design optimization calculation module 400 uses a large language model to convert the user's natural language information into input parameters for the planning module, and inputs them into the design optimization module through a preset interface. The design optimization module has a built-in database and model library. It constructs an optimization problem in the design optimization module, and performs optimal planning under various boundary conditions in a way that minimizes the total cost based on the built-in model library and database data. After calculation by the optimization algorithm, it generates the optimal design scheme of the system and various performance indicators of the system.

[0094] The optimization output module 500 is used to reconfigure the system capacity to obtain a custom capacity configuration based on the optimal system design scheme and various system performance indicators, and to design custom topology relationships for various energy utilization modules in the model library to obtain custom topology relationships. Based on the custom capacity configuration and custom topology relationships, and in conjunction with the model library and database, an optimization problem is constructed. The minimum daily operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is then performed at multiple time scales to output the optimization solution results.

[0095] In one embodiment of the present invention, the user's natural language information includes at least the geographical location of the energy system, latitude and longitude, type of power generating unit, usage status of energy storage modules, electricity demand, and carbon emission-related constraints; the database includes various types of data such as equipment data, meteorological data, grid connection policies, load data, and other data; the model library includes various types of data such as source-side models, grid-side models, load-side models, storage-side models, hydrogen-side data, and chemical data.

[0096] In one embodiment of the present invention, the optimization variables of the optimization algorithm include system design variables, namely the installed capacity of various energy technologies, and system operation variables, namely the operation strategies of each unit; the objective function of the optimization algorithm is to minimize the annualized system cost; the constraint equations of the optimization algorithm include multiple of the following: installed capacity constraints, total system carbon emission constraints, unit operation constraints, unit operation status calculation equations, system power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

[0097] In one embodiment of the present invention, the optimization module further includes a front-end interface.

[0098] Users can input custom capacity configurations and custom topology relationships through the front-end interface, and generate system reports based on the obtained optimization results.

[0099] In one embodiment of the present invention, optimizing the solution result includes:

[0100] This includes various factors such as system balance, system operating costs, load shedding, energy storage, and renewable energy consumption.

[0101] According to an embodiment of the present invention, a low-carbon energy system design and planning device based on source-grid-load-storage hydrogen chemical industry employs large language model technology to train the first professional large model in the field of low-carbon energy, and simultaneously establishes the first intelligent agent for energy knowledge processing and data parsing. Ultimately, the large language model can autonomously plan and design functions based on users' natural language questions, providing users with a user-friendly interactive experience and high-quality design and planning reports.

[0102] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A low-carbon energy system design and planning method based on source-grid-load-storage-chemical engineering, characterized in that, include: Obtain user natural language information; Constructing a large-scale planning model for low-carbon energy systems; The large-scale low-carbon energy system planning model includes a large language model and a planning module; The user's natural language information is input into the large language model to identify the user's intent, and the planning module is invoked based on the identified user intent; wherein, the planning module includes a database, a model library, a design optimization module, and a runtime optimization module; The user's natural language information is transformed into input parameters for the planning module through a large language model and then input into the design optimization module through a preset interface. The design optimization module has a built-in database and model library. An optimization problem is constructed in the design optimization module. Based on the built-in model library and database data, the optimal planning is carried out under various boundary conditions in a way that minimizes the total cost. After calculation by the optimization algorithm, the optimal design scheme of the system and various performance indicators of the system are generated. Based on the optimal system design scheme and various system performance indicators, the system capacity is reconfigured to obtain a custom capacity configuration, and the various energy utilization modules of the model library are designed to obtain a custom topology. Based on custom capacity configuration and custom topology, and combined with model library and database, an optimization problem is constructed. The daily minimum operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is then performed at multiple time scales to output the optimization results.

2. The method according to claim 1, characterized in that, The user's natural language information includes at least the energy system's geographical location, latitude and longitude, power unit type, energy storage module usage status, electricity demand, and carbon emission-related constraints; the database includes various types of data such as equipment data, meteorological data, grid connection policies, load data, and others; the model library includes various types of data such as source-side models, grid-side models, load-side models, storage-side models, hydrogen-side data, and chemical data.

3. The method according to claim 1, characterized in that, The optimization variables of the optimization algorithm include system design variables, namely the installed capacity of various energy technologies, and system operation variables, namely the operation strategies of each unit. The objective function of the optimization algorithm is to minimize the annualized cost of the system. The constraint equations of the optimization algorithm include multiple ones, such as installed capacity constraints, total carbon emission constraints of the system, unit operation constraints, unit operation status calculation equations, system power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

4. The method according to claim 1, characterized in that, The operation optimization module also includes a front-end interface. Users can input custom capacity configurations and custom topology relationships through the front-end interface, and generate system reports based on the obtained optimization results.

5. The method according to claim 1, wherein The optimization solution results include: This includes various factors such as system balance, system operating costs, load shedding, energy storage, and renewable energy consumption.

6. A low-carbon energy system design and planning device based on source-grid-load-storage hydrogen chemical industry, characterized in that, include: The user data acquisition module is used to acquire users' natural language information; The system model building module is used to build large-scale planning models for low-carbon energy systems. The large-scale low-carbon energy system planning model includes a large language model and a planning module; The model invocation module is used to input the user's natural language information into the large language model to identify the user's intent, and to invoke the planning module based on the identified user intent; wherein, the planning module includes a database, a model library, a design optimization module, and a runtime optimization module; The design optimization calculation module uses a large language model to transform the user's natural language information into input parameters for the planning module, and inputs them into the design optimization module through a preset interface. The design optimization module has a built-in database and model library. It constructs an optimization problem in the design optimization module, and performs optimal planning under various boundary conditions in a way that minimizes the total cost based on the built-in model library and database data. After calculation by the optimization algorithm, it generates the optimal design scheme of the system and various performance indicators of the system. The optimization output module is used to reconfigure the system capacity to obtain a custom capacity configuration based on the optimal system design scheme and various system performance indicators, and to design custom topology relationships for various energy utilization modules in the model library to obtain custom topology relationships. Based on the custom capacity configuration and custom topology relationships, and in conjunction with the model library and database, an optimization problem is constructed. The minimum daily operating cost is converted into an optimization objective in a preset format, and the operating strategies of each system component are converted into optimization variables in a preset format. The optimization is then performed at multiple time scales to output the optimization solution results.

7. The apparatus according to claim 6, characterized in that, The user's natural language information includes at least the energy system's geographical location, latitude and longitude, power unit type, energy storage module usage status, electricity demand, and carbon emission-related constraints; the database includes various types of data such as equipment data, meteorological data, grid connection policies, load data, and others; the model library includes various types of data such as source-side models, grid-side models, load-side models, storage-side models, hydrogen-side data, and chemical data.

8. The apparatus according to claim 6, characterized in that, The optimization variables of the optimization algorithm include system design variables, namely the installed capacity of various energy technologies, and system operation variables, namely the operation strategies of each unit. The objective function of the optimization algorithm is to minimize the annualized cost of the system. The constraint equations of the optimization algorithm include multiple ones, such as installed capacity constraints, total carbon emission constraints of the system, unit operation constraints, unit operation status calculation equations, system power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

9. The apparatus according to claim 6, characterized in that, The operation optimization module also includes a front-end interface. Users can input custom capacity configurations and custom topology relationships through the front-end interface, and generate system reports based on the obtained optimization results.

10. The apparatus according to claim 6, characterized in that, The optimization solution results include: This includes various factors such as system balance, system operating costs, load shedding, energy storage, and renewable energy consumption.

Images