Power dispatching control method and device based on large model

Abstract

The invention discloses a power dispatching control method and device based on a large model. The method comprises the following steps: acquiring a power dispatching request input by a user; inputting the power dispatching request into a preset demand analysis model to obtain a power dispatching demand corresponding to the power dispatching request; determining a plurality of scheduling sub-tasks and an execution sequence of each scheduling sub-task based on the power scheduling demand; and respectively inputting each scheduling sub-task into an execution analysis model, generating execution equipment and a control code corresponding to each scheduling sub-task, and controlling the scheduling content of the control equipment according to the execution sequence of each scheduling sub-task based on the execution equipment and the control code. The power dispatching request of the user is analyzed layer by layer through the large language model, and the accuracy of power dispatching is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent technology, and in particular to a large model-based power dispatching control method and device. Background Art

[0002] As the scale of power systems continues to expand and the complexity continues to increase, traditional manual power dispatch methods have been unable to meet the needs of modern power grids. At present, the conventional dispatching method of power systems is: rule-based power dispatching methods, which use preset rules and decision trees to dispatch power. This method automatically generates dispatch instructions based on the real-time power grid status by setting a series of dispatching rules. However, rule-based power dispatching methods lack flexibility and are difficult to cope with complex and changeable power grid conditions, and are prone to inaccurate power dispatching.

[0003] Therefore, there is an urgent need for a power dispatch control strategy to solve the problem of inaccurate power dispatch in rule-based power dispatch methods. Summary of the invention

[0004] The embodiment of the present invention provides a large model-based power dispatching control method and device to solve the problem of inaccurate power dispatching existing in the rule-based power dispatching method.

[0005] In order to solve the above problems, an embodiment of the present invention provides a large model-based power dispatching control method, including:

[0006] Obtaining the power dispatch request input by the user;

[0007] Input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; take the historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model;

[0008] Based on the power dispatching requirement, confirming a plurality of dispatching subtasks and the execution order of each of the dispatching subtasks; wherein a dispatching subtask corresponds to a power dispatching requirement;

[0009] Each of the scheduling subtasks is input into the execution analysis model respectively, and the execution device and control code corresponding to each of the scheduling subtasks are generated. Based on the execution device and the control code, the scheduling content of the control device is controlled according to the execution order of each of the scheduling subtasks; wherein, the historical scheduling subtask samples marked with the execution device and the control code are used as input, and the execution analysis model is used as output to train the large language model.

[0010] As an improvement of the above solution, the step of confirming a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes:

[0011] Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks;

[0012] Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

[0013] As an improvement of the above solution, the controlling of the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes:

[0014] Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order;

[0015] If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time.

[0016] If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

[0017] As an improvement of the above solution, the scheduling subtask includes: the scheduling order of the execution equipment, the parameters required for the execution equipment scheduling, and the processing method of the intermediate results generated by the execution equipment.

[0018] As an improvement of the above solution, after controlling the control device to schedule the content according to the execution order of each of the scheduling subtasks, the method further includes:

[0019] Collect operation data of control equipment;

[0020] Match the types and values ​​of operating data based on the preset fault database;

[0021] When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained;

[0022] When the match fails, no action is taken.

[0023] Accordingly, an embodiment of the present invention further provides a large model-based power dispatch control device, comprising: a data acquisition module, a demand analysis module, a task splitting module and a control dispatching module;

[0024] The data acquisition module is used to acquire the power dispatch request input by the user;

[0025] The demand analysis module is used to input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; using historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model;

[0026] The task splitting module is used to confirm a number of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand; wherein a scheduling subtask corresponds to a power scheduling demand;

[0027] The control scheduling module is used to input each of the scheduling subtasks into the execution analysis model respectively, generate the execution device and control code corresponding to each of the scheduling subtasks, and control the scheduling content of the control device according to the execution order of each of the scheduling subtasks based on the execution device and the control code; wherein the large language model is trained with historical scheduling subtask samples marked with execution devices and control codes as input and the execution analysis model as output.

[0028] As an improvement of the above solution, the step of confirming a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes:

[0029] Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks;

[0030] Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

[0031] As an improvement of the above solution, the controlling of the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes:

[0032] Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order;

[0033] If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time.

[0034] If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

[0035] As an improvement of the above solution, the scheduling subtask includes: the scheduling order of the execution equipment, the parameters required for the execution equipment scheduling, and the processing method of the intermediate results generated by the execution equipment.

[0036] As an improvement of the above solution, after controlling the control device to schedule the content according to the execution order of each of the scheduling subtasks, the method further includes:

[0037] Collect operation data of control equipment;

[0038] Match the types and values ​​of operating data based on the preset fault database;

[0039] When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained;

[0040] When the match fails, no action is taken.

[0041] As can be seen from the above, the present invention has the following beneficial effects:

[0042] The present invention provides a power dispatch control method based on a large model, comprising: obtaining a power dispatch request input by a user; inputting the power dispatch request into a preset demand analysis model to obtain a power dispatch demand corresponding to the power dispatch request; based on the power dispatch demand, confirming a number of dispatch subtasks and the execution order of each dispatch subtask; inputting each dispatch subtask into an execution analysis model respectively, generating an execution device and a control code corresponding to each dispatch subtask, and based on the execution device and the control code, controlling the dispatch content of the control device according to the execution order of each dispatch subtask. The present invention determines the power dispatch demand of the power dispatch request input by the user through a large model, and determines the dispatch subtask and the corresponding execution order by analyzing the power dispatch demand, and finally confirms the execution device and the control code of the dispatch subtask through a large language model, and controls the dispatch content of the control device through the execution order, thereby realizing the intelligentization of power dispatch. The power dispatch request of the user is analyzed layer by layer through a large language model, thereby improving the accuracy of power dispatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a large model-based power dispatching control method provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a large model-based power dispatching control device provided by an embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of the structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0047] Embodiment 1

[0048] See also Figure 1 , Figure 1 is a flow chart of a large model-based power dispatching control method provided by an embodiment of the present invention, such as Figure 1 As shown, this embodiment includes steps 101 to 104, and each step is specifically as follows:

[0049] Step 101: Obtain a power dispatch request input by a user.

[0050] Step 102: Input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; use historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model.

[0051] In this embodiment, the demand analysis model can identify the key points in the user's needs and obtain the tool information required to solve the task. The demand analysis model can quickly understand complex tasks through the powerful natural language processing capabilities of the large language model.

[0052] Step 103: Based on the power dispatching requirement, confirm a plurality of dispatching subtasks and the execution order of each of the dispatching subtasks; wherein a dispatching subtask corresponds to a power dispatching requirement.

[0053] In this embodiment, the step of determining a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes:

[0054] Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks;

[0055] Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

[0056] In a specific embodiment, several scheduling subtasks and the execution order of each scheduling subtask can be represented by a task tree structure. The characteristics of the task tree structure include: nodes: each node represents a subtask; levels: tasks are divided into different levels according to the dependencies of tasks; parallelism and sequence: for subtasks that can be processed in parallel, the task tree will arrange parallel execution, otherwise they will be executed sequentially.

[0057] In this embodiment, the scheduling subtask includes: the scheduling order of the execution device, the parameters required for the execution device scheduling, and the processing method of the execution device generating the intermediate results.

[0058] Step 104: Input each of the scheduling subtasks into the execution analysis model respectively, generate the execution device and control code corresponding to each of the scheduling subtasks, and control the scheduling content of the control device according to the execution order of each of the scheduling subtasks based on the execution device and the control code; wherein, the historical scheduling subtask samples marked with the execution device and the control code are used as input, and the execution analysis model is used as output to train the large language model.

[0059] In a specific embodiment, after the scheduling subtask planning is completed, the execution analysis model is called to write the corresponding code according to the task requirements. The code is used to execute the device and execute the scheduling task. To improve the accuracy of code generation, the system introduces the following optimizations:

[0060] 1. Code template library: For common power dispatching tasks, the system maintains a set of code template libraries. These templates can greatly improve the efficiency and accuracy of code generation.

[0061] 2. Syntax check and code optimization: After the code is generated, the system will automatically perform syntax check to ensure the correctness of the code. At the same time, code optimization is performed to reduce runtime errors.

[0062] It should be noted that the code written by the execution analysis model will be executed in a secure sandbox to prevent the code from having a destructive impact on the system. The sandbox mechanism provides an isolated environment to ensure the security of tool calls.

[0063] In this embodiment, controlling the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes:

[0064] Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order;

[0065] If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time.

[0066] If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

[0067] In this embodiment, after the control device performs the control of the scheduling content according to the execution order of each of the scheduling subtasks, the method further includes:

[0068] Collect operation data of control equipment;

[0069] Match the types and values ​​of operating data based on the preset fault database;

[0070] When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained;

[0071] When the match fails, no action is taken.

[0072] In a specific embodiment, the execution analysis model and the demand analysis model have self-diagnosis and debugging capabilities. The specific operations include:

[0073] 1. Error diagnosis: Analyze error information and determine the cause of the error;

[0074] 2. Automatic debugging: The system performs corresponding debugging operations based on the diagnosis results and tries to fix the errors;

[0075] 3. Limitation identification: The system can also identify problems that it cannot solve by itself, avoiding repeated attempts on the same problem, thereby improving overall system efficiency.

[0076] In a specific embodiment, the information after each task execution of the execution analysis model and the demand analysis model, including problems encountered, solutions, etc., will be stored in the experience pool. The experience pool can effectively improve the intelligence level of the system, and is specifically implemented as follows: the experience pool uses an efficient data structure to save problem descriptions, solutions, success rates and other information. Secondly, the retrieval algorithm: the system uses a semantic similarity algorithm to quickly retrieve similar historical problems in the experience pool to help the large language model quickly find reference solutions. The last part is the experience update mechanism: based on the latest execution results, the system will continuously optimize and update the data in the experience pool to ensure that the experience pool always remains efficient and accurate. For the specific implementation of experience pool maintenance, we can introduce the following mathematical formula to describe its core mechanism:

[0077] 1. Data structure design:

[0078] Let the experience pool E be a set, where each element e_i represents an experience record:

[0079] E = {e_1, e_2, ..., e_n};

[0080] Each experience record e_i can be represented as a vector:

[0081] e_i=(p_i,s_i,r_i,t_i);

[0082] Among them, p_i: problem description vector, s_i: solution vector, r_i: success rate (0≤r_i≤1), t_i: timestamp.

[0083] 2. Retrieval algorithm:

[0084] Cosine similarity is used to calculate semantic similarity. Given a new question q and a question p_i in the experience pool, the similarity is calculated as follows:

[0085] sim(q,p_i)=cos(q,p_i)=(q·p_i) / (||q||*||p_i||);

[0086] Where, represents the vector dot product, and ||x|| represents the Euclidean norm of vector x.

[0087] The retrieval process can be expressed as finding the most similar k experiences:

[0088] TopK=argmax_k(sim(q,p_i))for p_iin E.

[0089] 3. Experience update mechanism:

[0090] Define the experience update function U:

[0091] U(e_i,e_new)=(α*p_i+(1-α)*p_new,

[0092] β*s_i+(1-β)*s_new,

[0093] γ*r_i+(1-γ)*r_new,

[0094] t_new)

[0095] Among them, α, β, γ are weight parameters (0≤α, β, γ≤1), which are used to balance new and old experience. 4. Experience pool optimization:

[0096] Define the overall quality Q of the experience pool:

[0097] Q(E)=Σ(w_i*r_i) / |E|;

[0098] Where w_i is the weight of each experience, which can be calculated based on the time decay function: w_i = exp(-λ*(t_current-t_i));

[0099] λ is the time decay coefficient.

[0100] 5. Experience pool maintenance algorithm:

[0101] For new experiences e_new:

[0102] if sim(p_new,p_i)>threshold for any e_iin E:

[0103] e_i=U(e_i,e_new)

[0104] else:

[0105] E=E∪{e_new}

[0106] if|E|>max_size:

[0107] E=E-{argmin_e(w_e*r_e)}

[0108] 6. Perform optimization regularly:

[0109] while Q(E)<Q_threshold and|E|> min_size:

[0110] E=E-{argmin_e(w_e*r_e)}

[0111] It should be noted that the application scenarios of this embodiment include but are not limited to:

[0112] -Power flow calculation: dispatching tools to complete complex power flow analysis;

[0113] -Power dispatching: Help dispatchers to plan and execute tasks efficiently and accurately;

[0114] -Black start sequence: Automatically execute the sequential scheduling during the black start process of the power grid;

[0115] -Accident handling: quickly diagnose power system accidents and call for emergency handling tools;

[0116] -Scheme generation: Automatically generate the best execution plan based on the different task requirements of power dispatching.

[0117] In a specific embodiment, a specific motor control scheduling scheme example is given:

[0118] 1. Task understanding and planning: The demand analysis model receives the user's natural language query: "Please formulate a 24-hour optimal scheduling plan for the 10 high-power motors in the industrial park, taking into account grid load balancing and cost minimization."

[0119] The demand analysis model quickly understands the task requirements and develops a detailed execution plan: a) obtains grid load forecast data b) establishes a motor control optimization model c) solves the optimization problem d) generates a specific motor control solution e) monitors and adjusts in real time;

[0120] This kind of flexible task understanding and planning capability is difficult to achieve with traditional rule-based systems.

[0121] 2. Multi-tool collaborative calling: The execution analysis model automatically selects and calls multiple professional tools according to task requirements:

[0122] a) Call the load forecasting tool to obtain the 24-hour load curve of the power grid: L(t) = 10000 + 5000*sin(πt / 12)kW, 0≤t<24

[0123] b) Call the optimization modeling tool to build a motor control optimization model: Objective function: minimize max(L(t))-min(L(t)) Constraints:

[0124] ·ΣP_i(t)≤5000kW, i=1,2,...,10;

[0125] 0≤P_i(t)≤500kW;

[0126] The number of starts and stops of each motor is ≤3;

[0127] Single running time ≥ 2 hours.

[0128] c) Call the optimization solver to obtain the optimal control solution.

[0129] The seamless integration of these tools demonstrates its powerful tool calling and collaboration capabilities.

[0130] 3. Code generation and execution: Automatically generate Python code to implement optimization solutions: The ability to automatically generate and execute code based on task requirements greatly improves the flexibility and adaptability of the scheduling system.

[0131] 4. Real-time monitoring and dynamic adjustment: During the execution process, the motor operating status is continuously monitored.

[0132] When an abnormality is detected, such as when the temperature of motor 1 reaches 90°C (exceeding the threshold of 85°C) at t=10:00,

[0133] immediately:

[0134] a) Call the fault diagnosis tool to analyze the cause b) Generate a response strategy: reduce P_1(t) from 400kW to 300kW c) Reallocate 100kW load to other motors d) Notify maintenance personnel to check the bearings.

[0135] Real-time calculation of adjusted energy consumption and cost: E_new=∫[0,24](P_1_new(t) / η)dt≈

[0136] 5800kWh Cost_new=∫[0,24](P_1_new(t) / η*C(t))dt≈3480 yuan

[0137] This dynamic adjustment capability reflects the intelligent and adaptive characteristics of the execution analysis model and the demand analysis model.

[0138] 5. Experience learning and knowledge accumulation: After each scheduling task, the execution analysis model and the demand analysis model store the experience into the experience pool: e_i = (p_i, s_i, r_i, t_i) where p_i is the problem description vector (such as "motor overheating, bearing failure"), s_i is the solution vector, r_i is the success rate, and t_i is the timestamp.

[0139] When encountering similar situations in the future, the execution analysis model and the demand analysis model use semantic similarity for fast retrieval: sim(q,p_i)=(q·p_i) / (||q||*||p_i||);

[0140] If the similarity is higher than a threshold (such as 0.8), the execution analysis model and the demand analysis model will give priority to similar solutions to continuously improve scheduling efficiency and reliability.

[0141] This ability to continuously learn and accumulate knowledge is one of the key features that distinguishes execution analysis models and demand analysis models from traditional systems.

[0142] See also Figure 2 , Figure 2 It is a structural diagram of a large-model-based power dispatching control device provided by an embodiment of the present invention, comprising: a data acquisition module 201, a demand analysis module 202, a task splitting module 203 and a control scheduling module 204;

[0143] The data acquisition module is used to acquire the power dispatch request input by the user;

[0144] The demand analysis module is used to input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; using historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model;

[0145] The task splitting module is used to confirm a number of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand; wherein a scheduling subtask corresponds to a power scheduling demand;

[0146] The control scheduling module is used to input each of the scheduling subtasks into the execution analysis model respectively, generate the execution device and control code corresponding to each of the scheduling subtasks, and control the scheduling content of the control device according to the execution order of each of the scheduling subtasks based on the execution device and the control code; wherein the large language model is trained with historical scheduling subtask samples marked with execution devices and control codes as input and the execution analysis model as output.

[0147] As an improvement of the above solution, the step of confirming a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes:

[0148] Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks;

[0149] Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

[0150] As an improvement of the above solution, the controlling of the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes:

[0151] Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order;

[0152] If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time.

[0153] If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

[0154] As an improvement of the above solution, the scheduling subtask includes: the scheduling order of the execution equipment, the parameters required for the execution equipment scheduling, and the processing method of the intermediate results generated by the execution equipment.

[0155] As an improvement of the above solution, after controlling the control device to schedule the content according to the execution order of each of the scheduling subtasks, the method further includes:

[0156] Collect operation data of control equipment;

[0157] Match the types and values ​​of operating data based on the preset fault database;

[0158] When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained;

[0159] When the match fails, no action is taken.

[0160] This embodiment obtains the power dispatch request input by the user; inputs the power dispatch request into the preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; based on the power dispatch demand, confirms several dispatch subtasks and the execution order of each dispatch subtask; inputs each dispatch subtask into the execution analysis model respectively, generates the execution device and control code corresponding to each dispatch subtask, and based on the execution device and the control code, controls the dispatch content of the control device according to the execution order of each dispatch subtask. The present invention determines the power dispatch demand of the power dispatch request input by the user through a large model, and determines the dispatch subtask and the corresponding execution order by analyzing the power dispatch demand, and finally confirms the execution device and control code of the dispatch subtask through a large language model, and controls the dispatch content of the control device through the execution order, thereby realizing the intelligentization of power dispatch. The power dispatch request of the user is analyzed layer by layer by a large language model, which improves the accuracy of power dispatch.

[0161] Embodiment 2

[0162] See also Figure 3 , Figure 3 It is a schematic diagram of the structure of a terminal device provided in one embodiment of the present invention.

[0163] A terminal device of this embodiment includes: a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program, the steps of the above-mentioned large-model-based power dispatching control method in the embodiment are implemented, for example: Figure 1 Alternatively, when the processor executes the computer program, the functions of each module in the above-mentioned device embodiments are implemented, for example: Figure 2 All modules of the large model-based power dispatching control device are shown.

[0164] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the large model-based power dispatching control method as described in any of the above embodiments.

[0165] Those skilled in the art will understand that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0166] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 301 is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0167] The memory 302 can be used to store the computer program and / or module. The processor 301 implements various functions of the terminal device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0168] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0169] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0170] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A power dispatching control method based on a large model, characterized in that: include: Obtaining the power dispatch request input by the user; Input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; take the historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model; Based on the power dispatching requirement, confirming a plurality of dispatching subtasks and the execution order of each of the dispatching subtasks; wherein a dispatching subtask corresponds to a power dispatching requirement; Each of the scheduling subtasks is input into the execution analysis model respectively, and the execution device and control code corresponding to each of the scheduling subtasks are generated. Based on the execution device and the control code, the scheduling content of the control device is controlled according to the execution order of each of the scheduling subtasks; wherein, the historical scheduling subtask samples marked with the execution device and the control code are used as input, and the execution analysis model is used as output to train the large language model.

2. The large model-based power dispatching control method according to claim 1, characterized in that: The determining of a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes: Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks; Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

3. The large model-based power dispatching control method according to claim 1, characterized in that: The controlling of the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes: Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order; If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time. If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

4. The large model-based power dispatching control method according to claim 1, characterized in that: The scheduling subtask includes: the scheduling order of the execution equipment, the parameters required for the execution equipment scheduling, and the processing method of the intermediate results generated by the execution equipment.

5. The large model-based power dispatching control method according to any one of claims 1 to 4, characterized in that: After the control device performs the control of the scheduling content according to the execution order of each of the scheduling subtasks, the method further includes: Collect operation data of control equipment; Match the types and values ​​of operating data based on the preset fault database; When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained; When the match fails, no action is taken.

6. A large-scale model-based power dispatching control device, characterized in that: include: Data acquisition module, demand analysis module, task splitting module and control scheduling module; The data acquisition module is used to acquire the power dispatch request input by the user; The demand analysis module is used to input the power dispatch request into a preset demand analysis model to obtain the power dispatch demand corresponding to the power dispatch request; wherein the power dispatch demand includes: dispatch content and control equipment; using historical power dispatch request samples marked with power dispatch demand as input and the demand analysis model as output to train the large language model; The task splitting module is used to confirm a number of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand; wherein a scheduling subtask corresponds to a power scheduling demand; The control scheduling module is used to input each of the scheduling subtasks into the execution analysis model respectively, generate the execution device and control code corresponding to each of the scheduling subtasks, and control the scheduling content of the control device according to the execution order of each of the scheduling subtasks based on the execution device and the control code; wherein the large language model is trained with historical scheduling subtask samples marked with execution devices and control codes as input and the execution analysis model as output.

7. The large model-based power dispatching control device according to claim 6, characterized in that: The determining of a plurality of scheduling subtasks and the execution order of each scheduling subtask based on the power scheduling demand includes: Analyze the power dispatch demand through a task decomposition algorithm to obtain a number of dispatch subtasks and the dependency relationship between each of the dispatch subtasks; Based on the dependency relationship between the scheduling subtasks, the execution order of each scheduling subtask is determined.

8. The large model-based power dispatching control device according to claim 6, characterized in that: The controlling of the scheduling content of the control device according to the execution order of each of the scheduling subtasks includes: Determine whether there is a parallel order in the execution order of each of the scheduled subtasks; wherein the execution order includes: a parallel order and a sequential order; If it exists, the parallel scheduling subtask is marked as the target subtask group, and the control device corresponding to the scheduling subtask is controlled according to the sequence of the target subtask group and several non-parallel scheduling subtasks; wherein, when the target subtask group is executed, the control device corresponding to the scheduling subtask of the target subtask group is controlled according to the parallel sequence at the same time. If it does not exist, the control device is controlled to schedule the content according to the sequence of each of the scheduling subtasks.

9. The large model-based power dispatching control device according to claim 6, characterized in that: The scheduling subtask includes: the scheduling order of the execution equipment, the parameters required for the execution equipment scheduling, and the processing method of the intermediate results generated by the execution equipment.

10. The large model-based power dispatching control device according to any one of claims 6 to 9, characterized in that: After the control device performs the control of the scheduling content according to the execution order of each of the scheduling subtasks, the method further includes: Collect operation data of control equipment; Match the types and values ​​of operating data based on the preset fault database; When the match is successful, the fault response strategy of the control device corresponding to the operating data is retrieved from the fault database, and the data collection of the control device is maintained; When the match fails, no action is taken.

Images