Source network load storage rapid regulation and control cooperation method and system based on artificial intelligence

Abstract

The invention discloses a source network load storage rapid regulation and control cooperation method and system based on artificial intelligence, and the method comprises the steps: collecting multi-source heterogeneous data during the operation of an electric power system, inputting the data into a large model for semantic analysis, constructing a scene semantic vector used for describing the operation of the electric power system, and carrying out the semantic analysis; a plurality of prior power instruction values stored by the source network are generated; mapping each priori power instruction value to a feasible solution domain meeting the constraint condition of the power system, and finding out the priori power instruction value meeting the condition in all the priori power instruction values; and issuing the priori power instruction value meeting the condition to a power generation side, a power grid side, a load side and / or an energy storage side so as to realize rapid coordinated regulation and control of source, grid and load storage.

Description

Technical Field

[0001] This invention belongs to the field of rapid regulation and coordination technology of power generation, grid, load and storage, and more specifically, relates to a method and system for rapid regulation and coordination of power generation, grid, load and storage based on artificial intelligence. Background Technology

[0002] In the current field of power system operation and control, with the rapid increase in installed capacity of new energy sources and the intensification of the trend of high-proportion grid connection, the existing technical system faces unprecedented challenges. Traditional power system frequency regulation and load balancing methods mainly rely on conventional thermal power units, pumped storage, and demand response on part of the load side. These methods were able to maintain the frequency stability and supply-demand balance of the system well when the penetration rate of renewable energy in the grid was low in the past. However, with the large-scale integration of intermittent and fluctuating power sources such as wind power and photovoltaics, the inertia and slow speed of traditional unit regulation have become increasingly prominent, causing the grid to be prone to frequency deviation or even frequency instability under power imbalances at the second or even sub-second level. Most existing control measures adopt planned dispatch and ancillary service market mechanisms at the minute or longer time scale, lacking the ability to respond efficiently to rapid disturbances at the second level, and are unable to meet the rigid demand of high-proportion new energy grids for short-term time scale regulation. In addition, although energy storage systems are gradually being applied to the grid, the existing energy storage dispatch models are mostly based on intraday planning or simple rules, failing to fully explore their potential in second-level dynamic regulation, resulting in low utilization efficiency of energy storage resources.

[0003] Therefore, new modeling methods and optimization strategies are urgently needed to achieve second-level coordination and efficient utilization of multiple resources. Summary of the Invention

[0004] To address the above technical problems, this invention proposes a rapid coordinated regulation and control method for source-grid-load-storage systems based on artificial intelligence, comprising: Collect multi-source heterogeneous data of the power system during operation, input it into a large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​of source, grid, load and storage. Map each prior power command value to a feasible solution domain that satisfies the power system constraints, and find the prior power command values ​​that satisfy the conditions among all prior power command values; The prior power command value that meets the conditions is sent to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated regulation of source, grid, load and storage.

[0005] Furthermore, the constraints include: energy storage state of charge constraints and a renewable energy consumption rate of not less than 90%.

[0006] Furthermore, the large models include: multimodal models that integrate natural language processing and time series prediction capabilities, used to process both textual and numerical information simultaneously.

[0007] Furthermore, before identifying the a priori power command values ​​that meet the conditions among all priori power command values, the process includes: convexification using a mixed norm and auxiliary variables, where the nonlinear deviation term is replaced by a mixed representation of the L1 norm and L2 norm, and the absolute value term and nonconvex term are linearized using auxiliary variables.

[0008] Furthermore, it also includes: dividing the energy source, grid, load, and storage into three channels for regulation, including: energy storage channel, demand response channel, and cross-regional trading channel; The actual regulation power of each channel is calculated based on the prior power command value, specifically including: , , in, In time Time The actual adjustment power of each channel This is the starting time of the current regulatory window. This refers to the command response delay time, used to describe the response time of a power system to control commands. For channel response core, In time Time The prior power command value for each channel, As an energy storage channel, As a demand response channel, For cross-regional trading channels, For the first The effective coefficient of each channel For the first The base response latency of each channel For the first The actual response delay time of each channel This is an indicator function.

[0009] Furthermore, based on time Time Actual adjustment power of each channel Calculate the power system in time The net unbalanced power at that time specifically includes: , in, For the power system in time Net unbalanced power at that time In time The actual output of new energy sources In time The actual output of conventional generating units In time Time-based energy storage channel The actual regulating power, In time Time-based demand response channel The actual regulating power, In time Cross-regional trading channel The actual regulating power, In time The load demand power at that time In time The amount of load reduced in response to demand.

[0010] Furthermore, finding the a priori power command value that meets the conditions among all priori power command values ​​includes: setting the synthesis objective function, finding the priori power command value that minimizes the synthesis objective function among all priori power command values, and using it as the a priori power command value that meets the conditions. The comprehensive objective function is: , in, For the comprehensive objective function, As the weight of the energy storage channel, As the weight of the demand response channel, As the weight of cross-regional transaction channels, In time The user discomfort index is due to reduced demand response. The weight of the net imbalance power. This is a penalty for abandoning electricity. As a weight for the reserve capacity demand, This is the required amount of spare capacity.

[0011] This invention also proposes an artificial intelligence-based rapid regulation and coordination system for power generation, grid, load, and energy storage, comprising: The prior module is used to collect multi-source heterogeneous data during the operation of the power system, input it into the large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​for source, grid, load and storage. The query module is used to map each prior power command value to a feasible solution domain that satisfies the power system constraints, and to find the prior power command values ​​that satisfy the conditions among all prior power command values. The control module is used to send the prior power command value that meets the conditions to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated control of source, grid, load and energy storage.

[0012] Furthermore, the constraints include: energy storage state of charge constraints and a renewable energy consumption rate of not less than 90%.

[0013] Furthermore, the large models include: multimodal models that integrate natural language processing and time series prediction capabilities, used to process both textual and numerical information simultaneously.

[0014] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art: The technical solution of this invention constructs a second-level unbalanced closed loop, combines energy storage, demand-side response, and trading power, calculates net unbalanced power in real time, and describes the dynamic capabilities of each resource with a three-channel response, achieving rapid regulation with "30-second arrival" and high absorption rate (≥90%), significantly improving the rapid adjustment capability and flexible operation level of the power system, and realizing efficient management of short-term load fluctuations and the randomness of new energy power generation. Attached Figure Description

[0015] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention; Figure 2 This is a system structure diagram of Embodiment 2 of the present invention. Detailed Implementation

[0016] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0017] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0018] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0019] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0020] The display screen is used to show the user interface of each application.

[0021] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0022] Example 1 like Figure 1 As shown, this embodiment proposes a rapid coordinated regulation and control method for source-grid-load-storage based on artificial intelligence, including: Step 101: Collect multi-source heterogeneous data of the power system during operation, input it into the large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​of source, grid, load and storage. Specifically, large models include: multimodal models that integrate natural language processing and time series prediction capabilities, used to process both textual and numerical information simultaneously, such as LLM large models.

[0023] Preferably, the large model constructs a scenario semantic vector to describe the operation of the power system based on multi-source heterogeneous data (such as weather evolution, equipment status, market prices, alarms, network topology changes, and other textual and structured information), and generates multiple prior power command values ​​for source, grid, load, and storage.

[0024] Step 102: Map each prior power command value to a feasible solution domain that satisfies the power system constraints, and find the prior power command values ​​that satisfy the conditions among all prior power command values; Specifically, before finding the a priori power command values ​​that meet the conditions among all priori power command values, the process also includes: convexification through a mixed norm and auxiliary variables, wherein the nonlinear deviation term is replaced by a mixed representation of L1 norm and L2 norm, and the absolute value term and nonconvex term are linearized through auxiliary variables.

[0025] Specifically, the constraints include: energy storage state of charge constraints and new energy consumption rate constraints of not less than 90%.

[0026] Preferably, the energy storage state of charge constraint is as follows: , , in, In time The state of charge value of the energy storage at that time. In time The state of charge value of the energy storage at that time. For energy storage charging efficiency, To obtain time Time-based energy storage channel The negative part of the actual regulating power, that is, the absolute value of the energy storage discharge power. To obtain time Time-based energy storage channel The positive part of the actual regulating power, i.e., the charging power of energy storage. For the discharge efficiency of energy storage, For time steps, For the rated capacity of energy storage, This represents the minimum value of the energy storage state of charge. This represents the maximum value of the energy storage state of charge.

[0027] Specifically, the energy source, grid, load, and storage will be divided into three channels for regulation: energy storage channel, demand response channel, and cross-regional trading channel. Preferably, the demand response channel refers to the adjustable load on the user side (industrial plants, building air conditioning, charging piles, etc.), which supports the operation of the power grid system by reducing / transferring load.

[0028] The actual regulation power of each channel is calculated based on the prior power command value, specifically including: , , in, In time Time The actual adjustment power of each channel This is the starting time of the current regulatory window. This refers to the command response delay time, used to describe the response time of a power system to control commands. For channel response core, In time Time The prior power command value for each channel, As an energy storage channel, As a demand response channel, For cross-regional trading channels, For the first The effective coefficient of each channel ∈(0,1], used to describe the proportion of the actual available power response capability of a channel to the prior power command value. For the first The base response latency of each channel For the first The actual response delay time of each channel This is an indicator function.

[0029] Specifically, based on time Time Actual adjustment power of each channel Calculate the power system in time The net unbalanced power at that time specifically includes:

[0030] in, For the power system in time Net unbalanced power at that time In time The actual output of new energy sources In time The actual output of conventional generating units In time Time-based energy storage channel The actual regulating power, In time Time-based demand response channel The actual regulating power usually refers to the actual available trading power locally. In time Cross-regional trading channel The actual regulated power is used to describe the actual available trading power across regions. In time The load demand power at that time In time The amount of load reduced in response to demand.

[0031] Specifically, finding the prior power command value that meets the conditions among all prior power command values ​​includes: setting the synthesis objective function, finding the prior power command value that minimizes the synthesis objective function among all prior power command values, and using it as the prior power command value that meets the conditions; The comprehensive objective function is: , in, For the comprehensive objective function, As the weight of the energy storage channel, As the weight of the demand response channel, As the weight of cross-regional transaction channels, In time The user discomfort index is due to reduced demand response. The weight of the net imbalance power. This is a penalty for abandoning electricity.

[0032] Preferably, this embodiment provides the following formula for calculating time. User maladaptation index due to reduced demand response : , in, For users who are not comfortable with the first weight of the index, The second weighting of the index is not suitable for users. In time The amount of load reduced in response to demand.

[0033] Preferably, in this embodiment, the power curtailment penalty is calculated using the following formula. : Let in time wind and solar power curtailment Define the absorption rate: , The constraints are: , , , in, To contribute to the renewable energy that is actually absorbed by the power system. From time The absorption rate of renewable energy output within the initial 30-second window. To prevent the removal of the zero constant.

[0034] Step 103: The prior power command value that meets the conditions is sent to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated regulation of source, grid, load and storage.

[0035] Example 2 like Figure 2 As shown, this embodiment proposes an artificial intelligence-based rapid regulation and coordination system for power generation, grid, load, and energy storage, including: The prior module is used to collect multi-source heterogeneous data during the operation of the power system, input it into the large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​for source, grid, load and storage. Specifically, large models include: multimodal models that integrate natural language processing and time series prediction capabilities, used to process both textual and numerical information simultaneously, such as LLM large models.

[0036] Preferably, the large model constructs a scenario semantic vector to describe the operation of the power system based on multi-source heterogeneous data (such as weather evolution, equipment status, market prices, alarms, network topology changes, and other textual and structured information), and generates multiple prior power command values ​​for source, grid, load, and storage.

[0037] The query module is used to map each prior power command value to a feasible solution domain that satisfies the power system constraints, and to find the prior power command values ​​that satisfy the conditions among all prior power command values. Specifically, before finding the a priori power command values ​​that meet the conditions among all priori power command values, the process also includes: convexification through a mixed norm and auxiliary variables, wherein the nonlinear deviation term is replaced by a mixed representation of L1 norm and L2 norm, and the absolute value term and nonconvex term are linearized through auxiliary variables.

[0038] Specifically, the constraints include: energy storage state of charge constraints and new energy consumption rate constraints of not less than 90%.

[0039] Preferably, the energy storage state of charge constraint is as follows: , , in, In time The state of charge value of the energy storage at that time. In time The state of charge value of the energy storage at that time. For energy storage charging efficiency, To obtain time Time-based energy storage channel The negative part of the actual regulating power, that is, the absolute value of the energy storage discharge power. To obtain time Time-based energy storage channel The positive part of the actual regulating power, i.e., the charging power of energy storage. For the discharge efficiency of energy storage, For time steps, For the rated capacity of energy storage, This represents the minimum value of the energy storage state of charge. This represents the maximum value of the energy storage state of charge.

[0040] Specifically, the energy source, grid, load, and storage will be divided into three channels for regulation: energy storage channel, demand response channel, and cross-regional trading channel. Preferably, the demand response channel refers to the adjustable load on the user side (industrial plants, building air conditioning, charging piles, etc.), which supports the operation of the power grid system by reducing / transferring load.

[0041] The actual regulation power of each channel is calculated based on the prior power command value, specifically including: , , in, In time Time The actual adjustment power of each channel This is the starting time of the current regulatory window. This refers to the command response delay time, used to describe the response time of a power system to control commands. For channel response core, In time Time The prior power command value for each channel, As an energy storage channel, As a demand response channel, For cross-regional trading channels, For the first The effective coefficient of each channel ∈(0,1], used to describe the proportion of the actual available power response capability of a channel to the prior power command value. For the first The base response latency of each channel For the first The actual response delay time of each channel This is an indicator function.

[0042] Specifically, based on time Time Actual adjustment power of each channel Calculate the power system in time The net unbalanced power at that time specifically includes:

[0043] in, For the power system in time Net unbalanced power at that time In time The actual output of new energy sources In time The actual output of conventional generating units In time Time-based energy storage channel The actual regulating power, In time Time-based demand response channel The actual regulating power usually refers to the actual available trading power locally. In time Cross-regional trading channel The actual regulated power is used to describe the actual available trading power across regions. In time The load demand power at that time In time The amount of load reduced in response to demand.

[0044] Specifically, finding the prior power command value that meets the conditions among all prior power command values ​​includes: setting the synthesis objective function, finding the prior power command value that minimizes the synthesis objective function among all prior power command values, and using it as the prior power command value that meets the conditions; The comprehensive objective function is: , in, For the comprehensive objective function, As the weight of the energy storage channel, As the weight of the demand response channel, As the weight of cross-regional transaction channels, In time The user discomfort index is due to reduced demand response. The weight of the net imbalance power. This is a penalty for abandoning electricity.

[0045] Preferably, this embodiment provides the following formula for calculating time. User maladaptation index due to reduced demand response : , in, For users who are not comfortable with the first weight of the index, The second weighting of the index is not suitable for users. In time The amount of load reduced in response to demand.

[0046] Preferably, in this embodiment, the power curtailment penalty is calculated using the following formula. : Let in time wind and solar power curtailment Define the absorption rate: , The constraints are: , , , in, To contribute to the renewable energy that is actually absorbed by the power system. From time The absorption rate of renewable energy output within the initial 30-second window. To prevent the removal of the zero constant.

[0047] The control module is used to send the prior power command value that meets the conditions to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated control of source, grid, load and energy storage.

[0048] Example 3 This invention also proposes a storage medium storing multiple instructions, which are used to implement the aforementioned AI-based rapid regulation and coordination method for source-grid-load-storage systems.

[0049] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0050] Optionally, in this embodiment, the storage medium is configured to store program code for performing the method steps of Embodiment 1.

[0051] Example 4 This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the aforementioned AI-based rapid regulation and coordination method for source-grid-load-storage systems.

[0052] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0053] The storage medium can be used to store software programs and modules, such as the AI-based rapid regulation and coordination method for source-grid-load-storage in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned AI-based rapid regulation and coordination method for source-grid-load-storage. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] The processor can execute the method steps of Embodiment 1 by calling the information and application stored in the storage medium through the transmission system.

[0055] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0056] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0057] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0058] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0059] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0060] If the integrated unit is implemented as 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0061] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for rapid coordinated regulation of power generation, grid, load, and storage based on artificial intelligence, characterized in that, include: Collect multi-source heterogeneous data of the power system during operation, input it into a large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​of source, grid, load and storage. Map each prior power command value to a feasible solution domain that satisfies the power system constraints, and find the prior power command values ​​that satisfy the conditions among all prior power command values. The prior power command value that meets the conditions is sent to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated regulation of source, grid, load and storage.

2. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 1, characterized in that, The constraints include: energy storage state of charge constraints and a renewable energy consumption rate of not less than 90%.

3. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 1, characterized in that, The large model includes: A multimodal model that integrates natural language processing and time series prediction capabilities is used to process both textual and numerical information simultaneously.

4. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 1, characterized in that, Before identifying the a priori power command values ​​that meet the conditions among all priori power command values, the process includes: convexification using a mixed norm and auxiliary variables, where the nonlinear deviation term is replaced by a mixed representation of the L1 and L2 norms, and the absolute value term and nonconvex term are linearized using auxiliary variables.

5. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 1, characterized in that, Also includes: The energy source, grid, load, and storage system will be regulated through three channels: energy storage channel, demand response channel, and cross-regional trading channel. The actual regulation power of each channel is calculated based on the prior power command value, specifically including: , , in, In time Time The actual adjustment power of each channel This is the starting time of the current regulatory window. This refers to the command response delay time, used to describe the response time of a power system to control commands. For channel response core, In time Time The prior power command value for each channel, As an energy storage channel, As a demand response channel, For cross-regional trading channels, For the first The effective coefficient of each channel For the first The base response latency of each channel For the first The actual response delay time of each channel This is an indicator function.

6. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 5, characterized in that, According to the time Time Actual adjustment power of each channel Calculate the power system in time The net unbalanced power at that time specifically includes: , in, For the power system in time Net unbalanced power at that time In time The actual output of new energy sources In time The actual output of conventional generating units In time Time-based energy storage channel The actual regulating power, In time Demand Response Channel The actual regulating power, In time Cross-regional trading channel The actual regulating power, In time The load demand power at that time In time The amount of load reduced in response to demand.

7. The method for rapid coordinated regulation of source, grid, load, and storage based on artificial intelligence as described in claim 6, characterized in that, Finding the a priori power command value that meets the conditions among all priori power command values ​​includes: setting the synthesis objective function, finding the priori power command value that minimizes the synthesis objective function among all priori power command values, and using it as the a priori power command value that meets the conditions. The comprehensive objective function is: ， in, For the comprehensive objective function, As the weight of the energy storage channel, As the weight of the demand response channel, As the weight of cross-regional transaction channels, In time The user discomfort index is due to reduced demand response. The weight of the net imbalance power. This is a penalty for abandoning electricity. As a weight for the reserve capacity demand, This is the required amount of spare capacity.

8. A rapid regulation and coordination system for power generation, grid, load, and storage based on artificial intelligence, characterized in that: include: The prior module is used to collect multi-source heterogeneous data during the operation of the power system, input it into the large model for semantic parsing, construct a scenario semantic vector to describe the operation of the power system, and generate multiple prior power command values ​​for source, grid, load and storage. The query module is used to map each prior power command value to a feasible solution domain that satisfies the power system constraints, and to find the prior power command values ​​that satisfy the conditions among all prior power command values. The control module is used to send the prior power command value that meets the conditions to the generation side, grid side, load side and / or energy storage side to achieve rapid coordinated control of source, grid, load and storage.

9. The AI-based rapid regulation and coordination system for power generation, grid, load, and storage as described in claim 8, characterized in that, The constraints include: energy storage state of charge constraints and a renewable energy consumption rate of not less than 90%.

10. The AI-based rapid regulation and coordination system for power generation, grid, load, and energy storage as described in claim 8, characterized in that, The large model includes: A multimodal model that integrates natural language processing and time series prediction capabilities is used to process both textual and numerical information simultaneously.

Images