Task regulation and control method and device of electric power system and storage medium

Abstract

The invention discloses a task regulation and control method and device of an electric power system and a storage medium, and is suitable for the electric power system.The method comprises the steps that a knowledge graph of the electric power system is constructed based on multi-source heterogeneous data of the electric power system; wherein the multi-source heterogeneous data comprises power operation data, renewable energy data, meteorological data and power grid event information; acquiring real-time monitoring data of the power system, and updating the knowledge graph by using the real-time monitoring data; acquiring initial input data at the current time, and performing enhancement processing on the initial input data according to the updated knowledge graph to obtain enhanced input data; and inputting the enhanced input data into a pre-trained large language model, and outputting a corresponding task regulation and control suggestion. According to the method, the operation mechanism and the interaction characteristics of the power system can be deeply understood in combination with the knowledge graph and the large language model, so that the corresponding task regulation and control suggestions can be accurately output based on enhanced input data, and the task regulation and control effect of the power system can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a task control method, device and storage medium for a power system. Background Art

[0002] With the increasing complexity of the power system and the large-scale access of renewable energy, the operation mode of the power grid has undergone profound changes. Renewable energy sources such as wind power and photovoltaic power generation are characterized by randomness and intermittency, which brings huge challenges to the real-time regulation of the power system.

[0003] In recent years, the development of artificial intelligence and big data technology has provided new ideas for the control of power systems. By introducing large models, massive amounts of data can be processed and complex patterns can be mined from them. The data of power systems are characterized by multi-source heterogeneity and complex associations. The existing task scheduling methods of power systems are difficult to fully utilize the potential value of power system data, resulting in poor task control effects of power systems. Summary of the invention

[0004] The present invention provides a task control method, device and storage medium for an electric power system to solve the technical problem that the existing task scheduling method for the electric power system is difficult to fully utilize the potential value of the data of the electric power system, resulting in poor task control effect of the electric power system.

[0005] The present invention provides a task control method for an electric power system, which is applicable to an electric power system. The task control method for an electric power system comprises:

[0006] Based on the multi-source heterogeneous data of the power system, a knowledge graph of the power system is constructed; wherein the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information;

[0007] Acquire real-time monitoring data of the power system, and use the real-time monitoring data to update the knowledge graph; wherein the real-time monitoring data includes real-time load data, real-time meteorological data, and real-time event information;

[0008] Acquire initial input data at the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data;

[0009] The enhanced input data is input into a pre-trained large language model, and corresponding task control suggestions are output.

[0010] Furthermore, the knowledge graph of the power system is constructed based on the multi-source heterogeneous data of the power system, including:

[0011] Extracting key elements from the multi-source heterogeneous data as entities for constructing a knowledge graph, wherein the key elements include generator sets, wind speed, maintenance plans, and emergencies;

[0012] Defining the connection relationship and causal relationship between the entities;

[0013] Based on the entities, the connection relationships and the causal relationships, a knowledge graph of the power system is constructed.

[0014] Furthermore, the initial input data is enhanced according to the updated knowledge graph to obtain enhanced input data, including:

[0015] Extracting an entity set from the initial input data, and determining a triple set related to the entity set in the updated knowledge graph;

[0016] The triple set is converted into knowledge prompt data, and the initial input data is concatenated with the knowledge prompt data to obtain enhanced input data.

[0017] Furthermore, the step of inputting the enhanced input data into a pre-trained large language model and outputting corresponding task control suggestions includes:

[0018] Extracting key influencing factors in the updated knowledge graph, wherein the key influencing factors include wind power output, load demand and equipment status;

[0019] Calculate the weight of each key influencing factor;

[0020] Based on the key influencing factors, the weights and the enhanced input data, output corresponding task control suggestions

[0021] Furthermore, the expression of the knowledge graph is:

[0022] G=(ε,R,K)

[0023] Among them, G is the knowledge graph, ε is the entity set, R is the relationship set, and K is the triple set.

[0024] The present invention also provides a task control device for an electric power system, which is applicable to an electric power system. The task control device for the electric power system comprises:

[0025] A knowledge graph construction module, used to construct a knowledge graph of the power system based on multi-source heterogeneous data of the power system; wherein the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information;

[0026] A knowledge graph updating module, used to obtain real-time monitoring data of the power system and update the knowledge graph using the real-time monitoring data; wherein the real-time monitoring data includes real-time load data, real-time meteorological data and real-time event information;

[0027] An enhanced input data acquisition module is used to acquire the initial input data at the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data;

[0028] The task control suggestion output module is used to input the enhanced input data into the pre-trained large language model and output the corresponding task control suggestion.

[0029] Furthermore, the knowledge graph construction module is also used to:

[0030] Extracting key elements from the multi-source heterogeneous data as entities for constructing a knowledge graph, wherein the key elements include generator sets, wind speed, maintenance plans, and emergencies;

[0031] Defining the connection relationship and causal relationship between the entities;

[0032] Based on the entities, the connection relationships and the causal relationships, a knowledge graph of the power system is constructed.

[0033] Furthermore, the enhanced input data acquisition module is also used for:

[0034] Extracting an entity set from the initial input data, and determining a triple set related to the entity set in the updated knowledge graph;

[0035] The triple set is converted into knowledge prompt data, and the initial input data is concatenated with the knowledge prompt data to obtain enhanced input data.

[0036] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the task control method of the power system as described above is implemented.

[0037] The present invention also 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 task control method of the power system as described above.

[0038] The embodiment of the present invention constructs a knowledge graph of the power system, fuses and enhances the initial input data with the updated knowledge graph to obtain enhanced input data, and inputs the enhanced input data into a large language model. Combining the knowledge graph and the large language model can deeply understand the operation mechanism and interaction characteristics of the power system, so that based on the enhanced input data, corresponding task control suggestions can be accurately output, thereby effectively improving the task control effect of the power system.

[0039] Furthermore, the embodiments of the present invention can effectively improve the dynamic adaptability and real-time performance of the model by extracting an entity set from the initial input data, determining knowledge related to the entity set in the updated knowledge graph, generating knowledge prompts and enhancing the input, so that the model can quickly respond to dynamic changes in the power system, adapt to fluctuations in renewable energy and emergencies, and thus accurately achieve real-time intraday regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of a task control method of a power system provided by an embodiment of the present invention;

[0041] Figure 2 It is a structural diagram of a task control device of an electric power system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In the description of this application, it should be understood that 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 technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0044] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0045] See also Figure 1 The present invention provides a task control method for an electric power system, which is applicable to an electric power system. The task control method for an electric power system includes:

[0046] S1. Construct a knowledge graph of the power system based on the multi-source heterogeneous data of the power system; the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information;

[0047] In an embodiment of the present invention, power operation data includes generator set status, line load, voltage and frequency, etc., renewable energy data includes wind power data and photovoltaic data, meteorological data includes temperature, wind speed and solar radiation, etc., and power grid event information includes equipment maintenance information, equipment failure information and external event information, etc.

[0048] S2. Obtain real-time monitoring data of the power system and use the real-time monitoring data to update the knowledge graph; wherein the real-time monitoring data includes real-time load data, real-time meteorological data and real-time event information;

[0049] In an embodiment of the present invention, the knowledge graph can be dynamically updated based on the acquired real-time monitoring data to ensure that it contains the latest information and related connections of the power system, so as to provide a more accurate analysis for the large language model. The updating of the knowledge graph includes updating newly occurring events, equipment status changes, etc.

[0050] By updating the knowledge graph according to real-time monitoring data, the embodiments of the present invention can enable the updated graph to quickly respond to dynamic changes in the power system, thereby adapting to fluctuations in renewable energy and emergencies, achieving real-time intraday regulation, and improving the ability to respond to the increasingly complex operating environment of the power system, providing reliable technical support for the development of smart grids.

[0051] S3, obtaining the initial input data at the current time, and enhancing the initial input data according to the updated knowledge graph to obtain enhanced input data;

[0052] S4. Input the enhanced input data into the pre-trained large language model and output the corresponding task control suggestions.

[0053] In an embodiment of the present invention, after outputting the task control suggestion, the power system can perform task control based on the task control suggestion. After receiving the enhanced input data, the large language model uses its natural language understanding and generation capabilities to output the task control suggestion and its corresponding explanation for the current situation by prompting the specification and standardized definition of the output of the control behavior result of the project; and the embodiment of the present invention can also fine-tune the large language model based on the prompt project after outputting the task control suggestion, thereby realizing feedback adjustment and gradually improving the large language model to further improve the accuracy of task control.

[0054] In an embodiment of the present invention, a knowledge graph of the power system is constructed, and the initial input data is fused and enhanced with the updated knowledge graph to obtain enhanced input data, and the enhanced input data is input into a large language model. Combining the knowledge graph and the large language model can deeply understand the operation mechanism and interaction characteristics of the power system, so that the corresponding task control suggestions can be accurately output based on the enhanced input data, thereby effectively improving the task control effect of the power system.

[0055] In one embodiment, step S1, constructing a knowledge graph of the power system based on multi-source heterogeneous data of the power system, includes:

[0056] S11. Extract key elements from multi-source heterogeneous data as entities for constructing knowledge graphs. The key elements include generator sets, wind speed, maintenance plans, and emergencies.

[0057] S12. Define the connection relationship and causal relationship between entities;

[0058] In the embodiment of the present invention, the determination of the causal relationship may be:

[0059] Identify which entities influence events and which are affected, determine the specific relationships between entities, such as "cause", "affect", "precede", "follow", etc., understand how one entity causes changes in another entity through a series of events or state changes, involving direct causality (A directly causes B) or indirect causality (A causes B through C), consider external conditions and background factors, which may affect the causal relationship between entities. For example, the same event may lead to different results in different environments or conditions, and use logical reasoning to determine whether the causal relationship between entities is reasonable. For example, if entity A usually occurs before entity B, and B occurs every time A occurs, then it can be inferred that A may cause B, thereby determining the causal relationship between entities.

[0060] S13. Construct a knowledge graph of the power system based on entities, connection relationships, and causal relationships.

[0061] In the embodiment of the present invention, the expression of the knowledge graph is:

[0062] G=(ε,R,K)

[0063] K={(h,r,t)}

[0064] Among them, G is the knowledge graph, ε is the entity set, R is the relationship set, K is the triple set, h is the head entity, r is the relationship, and t is the tail entity, among which the connection relationship and the causal relationship constitute the relationship set.

[0065] In an embodiment of the present invention, after the knowledge graph is constructed, a knowledge representation learning method can be used to map entities and relationships in the knowledge graph to a low-dimensional vector space, where the optimization goal is:

[0066] h+r≈t

[0067] In the formula, is the vector representation of entity h, relation r, and entity t, and d is the vector dimension.

[0068] The loss function is:

[0069]

[0070] In the formula, K ' is the negative sample set, γ is the margin hyperparameter, [x] + =max(0,x).

[0071] In an embodiment of the present invention, by constructing a knowledge graph in the field of electric power, multi-source heterogeneous data and professional knowledge are integrated into the input of a large language model, so that the complex interactive relationship between power system operation data, meteorological data, equipment information, events, etc. can be deeply explored, thereby enhancing the model's understanding and regulation capabilities of the power system, which is conducive to improving the task regulation effect of the power system.

[0072] In one embodiment, step S3, performing enhancement processing on the initial input data according to the updated knowledge graph to obtain enhanced input data, includes:

[0073] S31, extracting an entity set from the initial input data, and determining a triple set related to the entity set in the updated knowledge graph;

[0074] In the embodiment of the present invention, the initial input data may be the initial data input when task regulation is required.

[0075] The embodiment of the present invention can be based on the current prediction task and the initial input data X input , using entity recognition technology, extract the entity set ε from the initial input datainput , and further find the triple set K related to the entity set from the updated knowledge graph relevant .

[0076] S31. Convert the triple set into knowledge prompt data, and concatenate the initial input data with the knowledge prompt data to obtain enhanced input data.

[0077] The embodiment of the present invention converts the retrieved triple (h, r, t) into knowledge prompt data K in natural language, and converts the initial input data X input It is concatenated with the knowledge hint data K to form an enhanced input sequence:

[0078] X enhanced =[X input ; K].

[0079] The embodiment of the present invention can effectively improve the dynamic adaptability and real-time performance of the model by extracting an entity set from the initial input data, determining knowledge related to the entity set in the updated knowledge graph, generating knowledge prompts and enhancing the input, so as to enable the model to quickly respond to dynamic changes in the power system, adapt to fluctuations in renewable energy and emergencies, and thus accurately realize real-time intraday regulation.

[0080] In one embodiment, step S4, inputting the enhanced input data into the pre-trained large language model, and outputting corresponding task control suggestions, includes:

[0081] S41, extracting key influencing factors in the updated knowledge graph, where the key influencing factors include wind power output, load demand, and equipment status;

[0082] S42. Calculate the weight of each key influencing factor;

[0083] In the embodiment of the present invention, each key influencing factor F={f1, f2, ..., f n The weight of} is calculated as follows:

[0084]

[0085] Among them, impact(f i ) represents the factor f i The degree of influence on regulatory decisions.

[0086] S43. Based on key influencing factors, weights and enhanced input data, output corresponding task control suggestions.

[0087] In the embodiment of the present invention, the large language model can call the influencing factor analysis algorithm through the interface, and when outputting the corresponding task regulation suggestions, the influencing factor analysis algorithm is called based on its decision-making process and decision results, thereby automatically generating natural language task regulation suggestions and explanation reports. The examples are as follows:

[0088] It is recommended to increase the backup generation capacity between 14:00 and 16:00, mainly because:

[0089] 1. Wind power output is expected to decrease (weight 50%): The wind speed decreases, resulting in a decrease in wind power output.

[0090] 2. Increased load demand (weight 30%): In hot weather, air conditioning usage increases and load rises.

[0091] 3. Equipment maintenance (weight 20%): Some units are under maintenance, and the power supply capacity is limited.

[0092] The embodiment of the present invention outputs interpretable control decisions. While providing control suggestions, it outputs an explanatory report based on key influencing factors and their weights, which can effectively enhance the dispatching personnel's trust in the model and facilitate its application in actual work, thereby effectively improving the efficiency and reliability of power system control work.

[0093] The implementation of the embodiments of the present invention has the following beneficial effects:

[0094] The embodiment of the present invention constructs a knowledge graph of the power system, fuses and enhances the initial input data with the updated knowledge graph to obtain enhanced input data, and inputs the enhanced input data into a large language model. Combining the knowledge graph and the large language model can deeply understand the operation mechanism and interaction characteristics of the power system, so that based on the enhanced input data, corresponding task control suggestions can be accurately output, thereby effectively improving the task control effect of the power system.

[0095] Furthermore, the embodiments of the present invention can effectively improve the dynamic adaptability and real-time performance of the model by extracting an entity set from the initial input data, determining knowledge related to the entity set in the updated knowledge graph, generating knowledge prompts and enhancing the input, so that the model can quickly respond to dynamic changes in the power system, adapt to fluctuations in renewable energy and emergencies, and thus accurately achieve real-time intraday regulation.

[0096] See also Figure 2 Based on the same inventive concept as the above embodiment, the present invention further provides a task control device for a power system, which is applicable to a power system. The task control device for a power system includes:

[0097] The knowledge graph construction module 10 is used to construct a knowledge graph of the power system based on multi-source heterogeneous data of the power system; wherein the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information;

[0098] The knowledge graph updating module 20 is used to obtain real-time monitoring data of the power system and update the knowledge graph using the real-time monitoring data; wherein the real-time monitoring data includes real-time load data, real-time meteorological data and real-time event information;

[0099] The enhanced input data acquisition module 30 is used to acquire the initial input data at the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data;

[0100] The task control suggestion output module 40 is used to input the enhanced input data into the pre-trained large language model and output the corresponding task control suggestion.

[0101] In one embodiment, the knowledge graph construction module 10 is further used to:

[0102] Extract key elements from multi-source heterogeneous data as entities for constructing knowledge graphs. Key elements include generator sets, wind speed, maintenance plans, and emergencies.

[0103] Define connections and causal relationships between entities;

[0104] Construct a knowledge graph of the power system based on entities, connection relationships, and causal relationships.

[0105] In one embodiment, the enhanced input data acquisition module 30 is further used to:

[0106] Extract an entity set from the initial input data, and determine a set of triples related to the entity set in the updated knowledge graph;

[0107] The triple set is converted into knowledge hint data, and the initial input data is concatenated with the knowledge hint data to obtain enhanced input data.

[0108] In one embodiment, the augmented input data is input into a pre-trained large language model, and the corresponding task control suggestions are output, including:

[0109] Extract key influencing factors from the updated knowledge graph, including wind power output, load demand, and equipment status;

[0110] Calculate the weight of each key influencing factor;

[0111] Based on key influencing factors, weights and enhanced input data, corresponding task control suggestions are output.

[0112] In one embodiment, the expression of the knowledge graph is:

[0113] G=(ε,R,K)

[0114] Among them, G is the knowledge graph, ε is the entity set, R is the relationship set, and K is the triple set.

[0115] The embodiment of the present invention constructs a knowledge graph of the power system, fuses and enhances the initial input data with the updated knowledge graph to obtain enhanced input data, and inputs the enhanced input data into a large language model. Combining the knowledge graph and the large language model can deeply understand the operation mechanism and interaction characteristics of the power system, so that based on the enhanced input data, corresponding task control suggestions can be accurately output, thereby effectively improving the task control effect of the power system.

[0116] Furthermore, the embodiments of the present invention can effectively improve the dynamic adaptability and real-time performance of the model by extracting an entity set from the initial input data, determining knowledge related to the entity set in the updated knowledge graph, generating knowledge prompts and enhancing the input, so that the model can quickly respond to dynamic changes in the power system, adapt to fluctuations in renewable energy and emergencies, and thus accurately achieve real-time intraday regulation.

[0117] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the task control method of the power system of any one of the above embodiments.

[0118] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment are implemented, such as the enhanced input data acquisition module 30 .

[0119] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device. For example, the enhanced input data acquisition module 30 is used to obtain the initial input data of the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data.

[0120] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate 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 may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0121] The processor may be a central processing unit (CPU), 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 is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0122] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, 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.

[0123] Among them, 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 this 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. Among them, 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. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, 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. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0124] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including 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 task control method of the power system as described in any one of the above embodiments.

[0125] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A task control method for a power system, characterized in that: Applicable to a power system, the task control method of the power system includes: Based on the multi-source heterogeneous data of the power system, a knowledge graph of the power system is constructed; wherein the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information; Acquire real-time monitoring data of the power system, and use the real-time monitoring data to update the knowledge graph; wherein the real-time monitoring data includes real-time load data, real-time meteorological data, and real-time event information; Acquire initial input data at the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data; The enhanced input data is input into a pre-trained large language model, and corresponding task control suggestions are output.

2. The task control method of the power system according to claim 1, characterized in that: The method of constructing a knowledge graph of the power system based on multi-source heterogeneous data of the power system includes: Extracting key elements from the multi-source heterogeneous data as entities for constructing a knowledge graph, wherein the key elements include generator sets, wind speed, maintenance plans, and emergencies; Defining the connection relationship and causal relationship between the entities; Based on the entities, the connection relationships and the causal relationships, a knowledge graph of the power system is constructed.

3. The task control method of the power system according to claim 1, characterized in that: The step of performing enhancement processing on the initial input data according to the updated knowledge graph to obtain enhanced input data includes: Extracting an entity set from the initial input data, and determining a triple set related to the entity set in the updated knowledge graph; The triple set is converted into knowledge prompt data, and the initial input data is concatenated with the knowledge prompt data to obtain enhanced input data.

4. The task control method of the power system according to claim 1, characterized in that: The step of inputting the enhanced input data into a pre-trained large language model and outputting corresponding task control suggestions includes: Extracting key influencing factors in the updated knowledge graph, wherein the key influencing factors include wind power output, load demand and equipment status; Calculate the weight of each key influencing factor; Based on the key influencing factors, the weights and the enhanced input data, corresponding task regulation suggestions are output.

5. The task control method of the power system according to claim 1, characterized in that: The expression of the knowledge graph is: G=(ε,R,K) Among them, G is the knowledge graph, ε is the entity set, R is the relationship set, and K is the triple set.

6. A task control device for an electric power system, characterized in that: Applicable to a power system, wherein the task control device of the power system comprises: A knowledge graph construction module, used to construct a knowledge graph of the power system based on multi-source heterogeneous data of the power system; wherein the multi-source heterogeneous data includes power operation data, renewable energy data, meteorological data and power grid event information; A knowledge graph updating module, used to obtain real-time monitoring data of the power system and update the knowledge graph using the real-time monitoring data; wherein the real-time monitoring data includes real-time load data, real-time meteorological data and real-time event information; An enhanced input data acquisition module is used to acquire the initial input data at the current time, and enhance the initial input data according to the updated knowledge graph to obtain enhanced input data; The task control suggestion output module is used to input the enhanced input data into the pre-trained large language model and output the corresponding task control suggestion.

7. The task control device of the power system according to claim 6, characterized in that: The knowledge graph construction module is also used to: Extracting key elements from the multi-source heterogeneous data as entities for constructing a knowledge graph, wherein the key elements include generator sets, wind speed, maintenance plans, and emergencies; Defining the connection relationship and causal relationship between the entities; Based on the entities, the connection relationships and the causal relationships, a knowledge graph of the power system is constructed.

8. The task control device of the power system according to claim 6, characterized in that: The enhanced input data acquisition module is further used for: Extracting an entity set from the initial input data, and determining a triple set related to the entity set in the updated knowledge graph; The triple set is converted into knowledge prompt data, and the initial input data is concatenated with the knowledge prompt data to obtain enhanced input data.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the task control method of the power system as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium 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 task control method of the power system according to any one of claims 1 to 5.

Images