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

Abstract

The invention discloses a low-carbon energy system design planning method and device based on source network load hydrogen storage chemical engineering. The method comprises the steps of obtaining natural language information of a user; constructing a low-carbon energy system planning large model; the low-carbon energy system planning large model comprises a large language model and a planning module. Inputting the natural language information of the user into the large language model to identify the intention of the user, and calling a planning module through the identified intention of the user; the user natural language information is converted into input data in a preset format to be input into the planning module, and a planning report is output through optimization solving of the planning module; and displaying a planning result corresponding to the planning report through a large language model. According to the method, the first energy knowledge processing and data analysis agent is established, finally, the large language model can provide a friendly interactive experience and a high-quality design planning report for the user according to the natural language questioning and autonomous planning design function of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of energy large-scale models, and in particular to a design and planning method and device for a low-carbon energy system based on source-grid-load hydrogen storage chemical industry. Background Art

[0002] In the field of energy big models, the existing big models are mainly focused on realizing knowledge question-and-answer functions, and mainly focus on a certain field of traditional power production / transmission. There is a lack of deep coupling models for multiple types of energy, multiple types of energy storage forms, and multiple application scenarios in the low-carbon field. The current implementation of intelligent bodies is mostly based on open source frameworks, such as LangChain. There are already a large number of tools available in the community, but there are no tools related to the planning and design of low-carbon energy systems, which require customized development. Although the current low-carbon energy system design and planning tools can cover conventional planning scenarios, it is difficult to meet the scenario requirements of the current low-carbon energy system. At the same time, they do not have open source conditions and do not have the ability to connect to big models. Therefore, it is necessary to independently develop low-carbon energy system design and planning tools.

[0003] The underlying principle of the big model determines that it cannot perform complex mathematical calculations, but the design planning involves complex optimization algorithms, which cannot be achieved by relying solely on the big model itself. Therefore, it is necessary to accurately call the design planning module through the big model to achieve this function. The intelligent tool library based on the open source framework does not have tools related to low-carbon energy system planning and design, and cannot realize the combination of big models and design planning.

[0004] The current low-carbon energy system planning tools have the following shortcomings: First, the model's functions are not comprehensive and detailed enough, and there is a lack of characterization of chemical fields such as methanol and ammonia, as well as a lack of characterization of the variable operating characteristics of some power generation technologies; second, the model lacks a built-in database, and some current planning tools still require manual input of some data; third, current planning tools generally do not have the ability to connect to large models, and some current tools have high usage thresholds and require certain professional knowledge to use; fourth, current tools are mostly based on simulation, and lack the ability to provide the best scheduling plan in real time. At the same time, the current planning tool methods lack multi-time scale 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 solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the present invention proposes a low-carbon energy system design and planning method based on source-grid-load-hydrogen storage chemical industry, which combines the large language model and planning and design tools into an intelligent entity, so that users can complete the planning and design of the low-carbon energy system with a low threshold in the form of natural language interaction.

[0007] Another object of the present invention is to propose a low-carbon energy system design and planning device based on source-grid-load hydrogen storage chemical industry.

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

[0009] Obtain user natural language information;

[0010] Constructing a large model for low-carbon energy system planning; the large model for low-carbon energy system planning 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] Inputting the user's natural language information into the large language model to identify the user's intention, and calling the planning module according to the identified user's intention;

[0012] The content of the user's natural language information is converted into input parameters of the planning module through a large language model, and is input into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, and an optimization problem is constructed in the design optimization module. According to the built-in model library model and database data, optimal planning is performed under various boundary conditions in a manner that minimizes the total cost, and the optimal design scheme of the system and various performance indicators of the system are generated after calculation by the optimization algorithm;

[0013] According to the optimal design scheme of the system and various performance indicators of the system, the system capacity is reconfigured to obtain a custom capacity configuration, and the topological relationship of various energy utilization modules of the model library model is customized to obtain a custom topological relationship; according to the custom capacity configuration and the custom topological relationship, and in combination with the model library and the database, the optimization problem is constructed, the lowest operating cost of the day is converted into an optimization target in a preset format, the operating strategy of each system component is converted into an optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution result.

[0014] The low-carbon energy system design and planning method based on source-grid-load hydrogen storage chemical industry in the embodiment of the present invention 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, longitude and latitude of the energy system, type of power unit, usage status of the energy storage module, power demand, and carbon emission related constraints; the database includes equipment data, meteorological data, access policy, load data and other data; the model library includes 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, i.e., installed capacity of various energy technologies, and system operation variables, i.e., 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 installed capacity constraints, system total carbon emission constraints, unit operation constraints, unit operation status calculation equations, system electric 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] Input custom capacity configuration and custom topology relationship through the front-end interface, and generate a system report based on the obtained optimization solution results through the front-end interface.

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

[0020] It includes system balance conditions, system operating costs, load loss conditions, energy storage conditions, and renewable energy consumption conditions.

[0021] To achieve the above-mentioned purpose, the present invention proposes, on the other hand, a low-carbon energy system design and planning device based on source-grid-load hydrogen storage chemical industry, comprising:

[0022] User data acquisition module, used to obtain user natural language information;

[0023] A system model building module is used to build a large model for low-carbon energy system planning; the large model for low-carbon energy system planning 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] A model calling module, used for inputting the user's natural language information into the large language model to identify the user's intention, and calling the planning module through the identified user's intention;

[0025] The design optimization calculation module converts the content of the user's natural language information into input parameters of the planning module through a large language model, and inputs them into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, and an optimization problem is constructed in the design optimization module. According to the built-in model library model and database data, the optimal planning is carried out under various boundary conditions in a way of minimizing the total cost, and the optimal design scheme of the system and various performance indicators of the system are generated after calculation by the optimization algorithm;

[0026] The optimization solution output module is used to reconfigure the system capacity according to the optimal design scheme of the system and various performance indicators of the system to obtain a customized capacity configuration, and to customize the topological relationship design of various energy utilization modules of the model library model to obtain a customized topological relationship; according to the customized capacity configuration and the customized topological relationship, and in combination with the model library and the database, the optimization problem is constructed, the lowest operating cost of the day is converted into an optimization target in a preset format, the operating strategy of each system component is converted into an optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution result.

[0027] The low-carbon energy system design and planning method and device based on source-grid-load-hydrogen storage and chemical industry in the embodiment of the present invention, based on the solution of data resource library and optimization algorithm library in the field of low-carbon energy, explores the development technology route of low-carbon system design platform covering the integration of energy, power and chemical industry, builds the first planning and design platform that meets the multi-energy heterogeneous coupling needs of low-carbon energy system, and uses 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 energy knowledge processing and data analysis intelligent body, and finally realizes that the large language model can independently plan and design functions according to the user's natural language questions, and can provide users with friendly interactive experience and high-quality design planning reports.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

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

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

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

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

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

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

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

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

[0037] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0039] The following describes a method and device for designing and planning a low-carbon energy system based on source-grid-load hydrogen storage chemical industry according to an embodiment of the present invention with reference to the accompanying drawings.

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

[0041] S1, obtain user natural language information;

[0042] S2, constructing a large model for low-carbon energy system planning; the large model for low-carbon energy system planning 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, inputting the user's natural language information into the large language model to identify the user's intention, and calling the planning module through the identified user's intention;

[0044] S4, converting the content of the user's natural language information into input parameters of the planning module through a large language model, and inputting 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 manner that minimizes the total cost according to the built-in model library model 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, according to the system optimal design plan 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 model are customized to obtain a custom topological relationship; according to the customized capacity configuration and the customized topological relationship, and in combination with the model library and the database, the optimization problem is constructed, the lowest operating cost of the day is converted into an optimization target in a preset format, the operating strategies of various system components are converted into optimization variables in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution results.

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

[0047] Specifically, the big 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 uses the search function to obtain the latest information or data. Based on the understood content and the retrieved information, it constructs an accurate, relevant, and helpful answer. The generated answer is presented to the user in the form of natural language.

[0048] In one embodiment of the present invention, the present invention can input the user's natural language information into the big language model to identify the user's intention, and call the planning module through the identified user's intention. If the planning module is selected, the big language model will generate a call command in the form of json. The json format is as follows Figure 2 As shown. Among them, "action" corresponds to the tool name, and "action_input" corresponds to the input parameter name and corresponding value of the tool. Longitude and latitude, power unit type, energy storage module usage status, power demand, and carbon emission-related constraints will be converted into input data in a preset format and passed to the low-carbon system design and planning tool. If the user does not enter the required parameters of the design and planning tool, the agent returns a prompt to the user to add the corresponding parameters. If the parameters meet the requirements, the agent calls the design and planning module with the user input parameters, and the design and planning module returns a planning report. The large language model summarizes and refines the planning report and returns the planning results to the user. As a whole Figure 3 shown.

[0049] Compared with existing energy system planning and design products, the present invention is more difficult to use because most existing products use graphical interfaces to drag and edit parameters or users fill in forms and run programs. The present invention combines a large language model and planning and design tools into an intelligent entity, which can enable users to complete low-carbon energy system planning and design in a natural language interactive form with low barriers.

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

[0051] The main components and logic of the planning module of the embodiment of the present invention are as shown in the attached Figure 4 As shown in the figure, it mainly consists of four parts: one is the database, as shown in the attached Figure 3 As shown in the figure, it mainly includes equipment data, meteorological data, access policy, load data and other data; the second is the model library, which mainly includes source side model, grid side model, load side model, storage side model, hydrogen and chemical data. The third is the design optimization module, the main principle is as shown in the attached figure. Figure 5 As shown; the fourth is the operation optimization module, the main principle is as shown in the attached Figure 6 shown.

[0052] Specifically, the present invention converts the user's natural language information into input data in a preset format and inputs it into the planning module, and outputs a planning report through the optimization solution of the planning module. The main operation logic is as follows:

[0053] The big model converts the energy system's geographical location, power unit type, power demand, carbon emission-related constraints, etc. contained in the user's natural language into input parameters for the planning module, and inputs them 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, which accesses the data in the database and model library and generates a capacity configuration plan through a specific optimization algorithm;

[0055] Based on the capacity configuration plan, the user makes customized connections and designs in the front-end interface of the operation optimization module, and the final scheduling plan is generated after optimization by the operation optimization module.

[0056] The schematic diagram of the design optimization module of the embodiment of the present invention is shown in the attached figure. Figure 5 As shown, the input data are the fixed capacity, longitude and latitude of the generator set, and the main components of the system, etc., which are converted into input parameters of the design optimization module by the large model according to the user input text.

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

[0058] Construct optimization problems in the design optimization module, combine various built-in model library models and database data, perform optimal planning under various boundary conditions in a way that minimizes total cost, and generate the optimal design solution and various performance indicators of the system after calculation by the optimization algorithm.

[0059] It can be understood that the optimization variables of the optimization algorithm of the design optimization module in the 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 installed capacity constraints, system carbon emission total constraints, unit operation constraints, unit operation status calculation equations, system electric power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

[0060] Specifically, taking the "photovoltaic storage and charging integrated system" as an example, the input parameters are the photovoltaic output curve, charging demand curve, grid-connected electricity price, energy storage cost and other technical and economic parameters. The planning goal is to maximize the annualized profit of the system:

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

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

[0063] The constraints include:

[0064] (1) Capacity Limitation Constraints:

[0065] 0.2≤SOC(t)≤0.9

[0066] It indicates that the energy storage battery should operate in a certain state of charge range.

[0067] (2) Capacity recovery constraints:

[0068] SOC start =SOC end

[0069] It indicates that the energy storage battery returns to its initial charge state after an operation 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 at the same time.

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

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

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

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

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

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

[0079] Further, the schematic diagram of the operation optimization module is shown in the attached Figure 6 As shown in the figure, it mainly includes three main components: the front end that can interact with users, the model library database, and the optimization algorithm.

[0080] Specifically, the user performs customized connection and design in the front-end interface of the operation optimization module based on the capacity configuration plan, and generates the final scheduling plan after optimization by the operation optimization module, which may include:

[0081] Based on the calculation results of the design optimization module, namely the optimal design scheme of the system and various performance indicators of the system, users can independently reconfigure the capacity and design customized topological relationships for various energy utilization modules.

[0082] According to the customized capacity configuration and customized topological relationship, and in combination with the model library and database, the optimization problem is constructed, the lowest operating cost of the day is converted into the optimization target in a preset format, the operation strategy of each system component is converted into the optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution results.

[0083] It is understandable that the operation optimization module constructs the optimization problem based on the various capacity configurations and topological relationships input by the user, combined with the model library and database, and optimizes at multiple time scales at the same time, performing rolling optimization from three perspectives: day-ahead, intraday, and real-time, to guide actual production. The operation optimization module will eventually deliver the optimization results to the front end to feed back to the user. A system report can be generated through the front-end interface based on the obtained optimization solution results.

[0084] It can be known that the optimization solution results generated by the operation optimization module include: system balance, system operation cost, load loss, energy storage, and renewable energy consumption.

[0085] For example, taking the "photovoltaic storage and charging integrated system" as an example, the operation optimization module first predicts the light level and load demand in the next day with a resolution of 60 minutes, and uses this as an input parameter to obtain the system operation strategy in the next day, that is, intraday optimization. In the intraday rolling optimization, the resolution will be 15 minutes, and the prediction time domain will be 4 hours. The day-ahead optimization results will be corrected, such as modifying the distribution of photovoltaic output and the operating curve of battery energy storage. In real-time optimization, the resolution will be 1 minute, and the prediction time domain will be 5 minutes. The output of the fast unit will be adjusted to compensate for the fluctuations in load demand and renewable energy generation.

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

[0087] Based on the reality that the current smart energy platform focuses on energy-electricity-heat / steam, through in-depth research on the independent optimization of energy, electricity, and chemical industry in the current low-carbon energy field, as well as the high threshold for using traditional planning and design platforms, we research and develop innovative technical methods, including establishing a data resource and optimization algorithm library, developing the first low-carbon system planning and design module for energy-electricity-material collaborative optimization, and realizing an intelligent entity in the low-carbon energy field with a large model as the decision-making center and a design and planning module as a tool library, so as to solve the key technical difficulties in the smart low-carbon energy system planning and design platform, and achieve the goal of building a smart low-carbon energy system planning and design platform with natural language as the interactive form.

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

[0089] In order to implement the above embodiment, 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 chemical industry, including:

[0090] The 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 model for low-carbon energy system planning; the large model for low-carbon energy system planning 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] A model calling module 300 is used to input user natural language information into a large language model to identify user intent, and call a planning module through the identified user intent;

[0093] The design optimization calculation module 400 converts the content of the user's natural language information into input parameters of the planning module through a large language model, and inputs the information into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, and an optimization problem is constructed in the design optimization module. According to the built-in model library model and database data, the optimal planning is performed under various boundary conditions in a manner of minimizing the total cost, and the optimal design scheme of the system and various performance indicators of the system are generated after calculation by the optimization algorithm;

[0094] The optimization solution output module 500 is used to reconfigure the system capacity according to the system optimal design plan and various system performance indicators to obtain a customized capacity configuration, and to customize the topological relationship design of various energy utilization modules of the model library model to obtain a customized topological relationship; according to the customized capacity configuration and the customized topological relationship, and in combination with the model library and the database, the optimization problem is constructed, the lowest operating cost of the day is converted into an optimization target in a preset format, the operating strategy of each system component is converted into an optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution result.

[0095] In one embodiment of the present invention, the user's natural language information includes at least the geographical location, longitude and latitude of the energy system, the type of power unit, the usage status of the energy storage module, the power demand, and carbon emission-related constraints; the database includes equipment data, meteorological data, access policy, load data and other data; the model library includes 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, i.e., installed capacity of various energy technologies, and system operation variables, i.e., 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 installed capacity constraints, system carbon emission total constraints, unit operation constraints, unit operation status calculation equations, system electric power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

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

[0098] Input custom capacity configuration and custom topology relationship through the front-end interface, and generate a system report based on the obtained optimization solution results through the front-end interface.

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

[0100] It includes system balance conditions, system operating costs, load loss conditions, energy storage conditions, and renewable energy consumption conditions.

[0101] According to the low-carbon energy system design and planning device based on source-grid-load-hydrogen storage chemical industry of the embodiment of the present invention, the large language model technology is used to train the first professional large model in the field of low-carbon energy, and at the same time, the first energy knowledge processing and data analysis intelligent entity is established, and finally the large language model can independently plan the design function according to the user's natural language questions, and provide users with friendly interactive experience and high-quality design planning reports.

[0102] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0103] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

Claims

1. A design and planning method for a low-carbon energy system based on source-grid-load hydrogen storage chemical industry, characterized in that: include: Obtain user natural language information; Build a large-scale model for low-carbon energy system planning; The low-carbon energy system planning large model includes a large language model and a planning module; Inputting the user's natural language information into the large language model to identify the user's intention, and calling the planning module through the identified user's intention; wherein the planning module includes a database, a model library, a design optimization module and an operation optimization module; The content of the user's natural language information is converted into input parameters of the planning module through a large language model, and is input into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, and an optimization problem is constructed in the design optimization module. According to the built-in model library model and database data, optimal planning is performed under various boundary conditions in a manner that minimizes the total cost, and the optimal design scheme of the system and various performance indicators of the system are generated after calculation by the optimization algorithm; According to the optimal design scheme of the system and various performance indicators of the system, the system capacity is reconfigured to obtain a customized capacity configuration, and various energy utilization modules of the model library model are customized to design a customized topological relationship to obtain a customized topological relationship; According to the customized capacity configuration and customized topological relationship, and in combination with the model library and database, the optimization problem is constructed, the lowest operating cost of the day is converted into the optimization target in a preset format, the operation strategy of each system component is converted into the optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution results.

2. The method according to claim 1, characterized in that The user natural language information includes at least the geographical location, longitude and latitude of the energy system, type of power unit, usage status of the energy storage module, power demand, and carbon emission-related constraints; the database includes equipment data, meteorological data, access policy, load data and other data; the model library includes 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, i.e., installed capacity of various energy technologies, and system operation variables, i.e., 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 installed capacity constraints, total carbon emission constraints of the system, unit operation constraints, unit operation status calculation equations, system electric 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. Input custom capacity configuration and custom topology relationship through the front-end interface, and generate a system report based on the obtained optimization solution results through the front-end interface.

5. The method according to claim 1, characterized in that The optimization solution results include: It includes system balance conditions, system operating costs, load loss conditions, energy storage conditions, and renewable energy consumption conditions.

6. A low-carbon energy system design and planning device based on source-grid-load hydrogen storage chemical industry, characterized in that: include: User data acquisition module, used to obtain user natural language information; System model building module, used to build a large model for low-carbon energy system planning; The low-carbon energy system planning large model includes a large language model and a planning module; A model calling module, used to input the user's natural language information into the large language model to identify the user's intention, and call the planning module through the identified user's intention; wherein the planning module includes a database, a model library, a design optimization module and an operation optimization module; The design optimization calculation module converts the content of the user's natural language information into input parameters of the planning module through a large language model, and inputs them into the design optimization module through a preset interface; the design optimization module has a built-in database and model library, and an optimization problem is constructed in the design optimization module. According to the built-in model library model and database data, the optimal planning is carried out under various boundary conditions in a way of minimizing the total cost, and the optimal design scheme of the system and various performance indicators of the system are generated after calculation by the optimization algorithm; The optimization solution output module is used to reconfigure the system capacity according to the optimal design scheme of the system and various performance indicators of the system to obtain a customized capacity configuration, and to customize the topological relationship design of various energy utilization modules of the model library model to obtain a customized topological relationship; according to the customized capacity configuration and the customized topological relationship, and in combination with the model library and the database, the optimization problem is constructed, the lowest operating cost of the day is converted into an optimization target in a preset format, the operating strategy of each system component is converted into an optimization variable in a preset format, and the optimization solution is performed at multiple time scales to output the optimization solution result.

7. The device according to claim 6, characterized in that The user natural language information includes at least the geographical location, longitude and latitude of the energy system, type of power unit, usage status of the energy storage module, power demand, and carbon emission-related constraints; the database includes equipment data, meteorological data, access policy, load data and other data; the model library includes source side models, grid side models, load side models, storage side models, hydrogen side data and chemical data.

8. The device according to claim 6, characterized in that The optimization variables of the optimization algorithm include system design variables, i.e., installed capacity of various energy technologies, and system operation variables, i.e., 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 installed capacity constraints, total carbon emission constraints of the system, unit operation constraints, unit operation status calculation equations, system electric power balance equations, system annualized cost equations, and system annual carbon emission calculation equations.

9. The device according to claim 6, characterized in that The operation optimization module also includes a front-end interface. Input custom capacity configuration and custom topology relationship through the front-end interface, and generate a system report based on the obtained optimization solution results through the front-end interface.

10. The device according to claim 6, characterized in that The optimization solution results include: It includes system balance conditions, system operating costs, load loss conditions, energy storage conditions, and renewable energy consumption conditions.

Images