Intelligent decision-making method, device and equipment based on large model and storage medium

Abstract

The invention relates to the technical field of intelligent power plants, in particular to an intelligent decision-making method, device and equipment based on a large model and a storage medium. Power generation influence data influencing power generation of a power plant can be determined by determining the power plant type of the power plant and a power generation influence factor corresponding to the power plant type; and finally, generating an intelligent decision-making scheme corresponding to the power plant through the constructed target intelligent decision-making model, so as to control the power generation power of the power plant, improve the power generation power of the power plant and improve the power generation income. The technical problem that the income is uncontrollable in the power generation operation process of a power plant in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart power plants, and in particular to a large model-based intelligent decision-making method, device, equipment and storage medium. Background Art

[0002] During the operation of existing power plants, the power plant revenue will be affected by factors such as the operating status of the generator sets, the on-grid electricity price and the power generation efficiency, resulting in the power plant revenue being in an uncontrollable state and unable to achieve maximum benefits.

[0003] Taking thermal power plants as an example, the factors affecting the profits of thermal power generation include unit status, unit power generation efficiency, desulfurization and denitrification efficiency, grid-connected electricity price, load response rate and other factors; the factors affecting the power generation profits of hydropower plants include inflow, water level, load, adjustable range, output amplitude, vibration zone and other factors. The power generation influencing factors of power generation profits of different types of power plants are different and difficult to control.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide an intelligent decision-making method, device, equipment and storage medium based on a large model, aiming to solve the technical problem of uncontrollable benefits during the power generation operation of a power plant in the prior art.

[0006] To achieve the above object, the present invention provides an intelligent decision-making method based on a large model, the method comprising the following steps:

[0007] Determining a power plant type of a target power plant and a power generation impact factor corresponding to the power plant type;

[0008] Acquire a large data sample of power generation impact data corresponding to the power generation impact factor;

[0009] Building a target intelligent decision-making model based on the big data sample of the power generation impact data;

[0010] Generate an intelligent decision-making plan for the target power plant through the target intelligent decision-making model to control the power generation power of the target power plant;

[0011] The operating state of the target power plant is controlled based on the intelligent decision-making scheme.

[0012] Optionally, generating the intelligent decision-making scheme of the target power plant by using the target intelligent decision-making model includes:

[0013] Acquiring the current operating status and current power generation data of the target power plant;

[0014] Determine at least one candidate decision solution based on a decision database, the current power generation data, and the current working state, wherein the decision database corresponds to a power plant type of the target power plant;

[0015] The applicability of each candidate decision plan is evaluated through the target intelligent decision model to determine the intelligent decision plan of the target power plant from the candidate decision plans.

[0016] Optionally, the evaluating the applicability of each candidate decision solution through the target intelligent decision model to determine the intelligent decision solution of the target power plant from each candidate decision solution includes:

[0017] Splitting the control actions between the current working state and the candidate decision scheme to obtain at least two target control actions;

[0018] Calculating the continuous control cost of the current working state through the at least two target control actions based on the power generation impact factor;

[0019] Performing a suitability evaluation on the candidate decision scheme based on the continuous control cost corresponding to the continuous control action;

[0020] The candidate decision schemes that pass the applicability evaluation are used as the intelligent decision schemes of the target power plant.

[0021] Optionally, the evaluating the applicability of the candidate decision solutions based on the continuous control costs corresponding to each control action includes:

[0022]

[0023] Among them, c(s t ,s t+1 ) refers to the control cost of adjusting the current working state to the first target control action, c(s t ,s t+1 ) refers to the control cost of adjusting the first target control action to the second target control action, λ is the attenuation factor corresponding to the power plant type, δ is the slack variable, φ(s t ) is a preset evaluation function used to evaluate the benefits of the final operating state of the target power plant.

[0024] Optionally, after obtaining the big data sample of power generation impact data corresponding to the power generation impact factor, the method further includes:

[0025] Determining data characteristics of the big data sample of power generation impact data;

[0026] Based on the conversion strategy corresponding to the data characteristics of each large data sample, the large data sample is converted into target data of a unified category to obtain a target data set to be processed;

[0027] Accordingly, the target intelligent decision-making model is constructed based on the big data sample of the power generation influencing data, including:

[0028] A target intelligent decision-making model is constructed based on the target data set to be processed.

[0029] Optionally, controlling the operating state of the target power plant based on the intelligent decision-making solution includes:

[0030] Obtain the peak and valley electricity prices of the local power grid and the power generation quota of the power plant;

[0031] Modifying the intelligent decision-making scheme according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making scheme;

[0032] The operating state of the target power plant is controlled according to the target intelligent decision-making scheme.

[0033] Optionally, the intelligent decision-making scheme is corrected according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making scheme, including:

[0034] Determine the allocation ratio for each time period based on the peak and valley electricity prices of the local power grid and the corresponding impact coefficients;

[0035] Determine the target power generation quota for each time period according to the allocation ratio and the power generation quota of the power plant;

[0036] The intelligent decision-making plan is modified based on the power generation quota to adjust the working status of the target power plant in each time period to obtain a target intelligent decision-making plan.

[0037] In addition, to achieve the above purpose, the present invention also proposes an intelligent decision-making device based on a large model, and the intelligent decision-making device based on a large model includes:

[0038] A determination module, used to determine the power plant type of the target power plant and the power generation impact factor corresponding to the power plant type;

[0039] An acquisition module, used to acquire a large data sample of power generation impact data corresponding to the power generation impact factor;

[0040] A building module, used for building a target intelligent decision-making model based on the big data sample of the power generation impact data;

[0041] A generation module, used to generate an intelligent decision-making plan of the target power plant through the target intelligent decision-making model to control the power generation power of the target power plant;

[0042] A control module is used to control the operating state of the target power plant based on the intelligent decision-making solution.

[0043] In addition, to achieve the above-mentioned objectives, the present invention also proposes a big model-based intelligent decision-making device, which includes: a memory, a processor, and a big model-based intelligent decision-making program stored in the memory and executable on the processor, and the big model-based intelligent decision-making program is configured to implement the steps of the big model-based intelligent decision-making method described above.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which an intelligent decision-making program based on a large model is stored. When the intelligent decision-making program based on a large model is executed by a processor, the steps of the intelligent decision-making method based on a large model as described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the large model-based intelligent decision-making method as described above.

[0046] One or more technical solutions proposed in the present invention have at least the following technical effects: the present invention discloses an intelligent decision-making method based on a large model, and the intelligent decision-making method based on the large model includes: determining the power plant type of a target power plant and the power generation influencing factor corresponding to the power plant type; obtaining a large data sample of power generation influencing data corresponding to the power generation influencing factor; constructing a target intelligent decision-making model based on the large data sample of the power generation influencing data; generating an intelligent decision-making plan for the target power plant through the target intelligent decision-making model to control the power generation of the target power plant; and controlling the operating state of the target power plant based on the intelligent decision-making plan. Compared with the prior art, the present invention can determine the power plant type of the power plant and the power generation influencing factor corresponding to the power plant type, thereby determining the power generation influencing data affecting the power generation of the power plant, and correspondingly obtaining a large data sample of the power generation influencing data, thereby improving the fitting degree of the constructed intelligent decision-making model, and finally generating an intelligent decision-making plan corresponding to the power plant through the constructed target intelligent decision-making model to control the power generation of the power plant, improve the power generation of the power plant, and improve the power generation income, thereby avoiding the technical problem of uncontrollable income during the power generation operation of the power plant in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 It is a flow chart of the first embodiment of the intelligent decision-making method based on a large model of the present invention;

[0050] Figure 2 It is a flow chart of the second embodiment of the intelligent decision-making method based on a large model of the present invention;

[0051] Figure 3 It is a flow chart of the third embodiment of the intelligent decision-making method based on a large model of the present invention;

[0052] Figure 4 It is a structural block diagram of the first embodiment of the intelligent decision-making device based on a large model of the present invention;

[0053] Figure 5 It is a structural diagram of a large-model-based intelligent decision-making device in a hardware operating environment involved in an embodiment of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] Based on this, the embodiment of the present invention provides an intelligent decision-making method based on a large model. Figure 1 , Figure 1 The figure is a flow chart of the first embodiment of an intelligent decision-making method based on a large model of the present invention.

[0058] In this embodiment, the intelligent decision-making method based on the large model includes:

[0059] Step S10: Determine the power plant type of the target power plant and the power generation impact factor corresponding to the power plant type.

[0060] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a control computer, etc. The following takes the control computer as an example to illustrate this embodiment and the following embodiments.

[0061] It should be noted that traditional power plants include but are not limited to thermal power generation, hydropower generation, photovoltaic power generation, nuclear power, etc. For some large power plants, there is a minimum power generation requirement for each period. On this basis, the remaining power generation can be connected to the power grid to obtain profits. For some small power plants, there is no minimum power generation requirement. They only need to connect the electricity obtained through various means into the power grid to obtain profits.

[0062] However, electricity storage also requires a certain cost, and the currently generated electricity will not be directly connected to the power grid. In addition, except for wind power generation and photovoltaic power generation, whose costs are not subject to human control, other types of power plants can achieve precise control of power generation by controlling the operating status of the generator set or the amount of fuel. However, in traditional power generation technology, the operation of the generator set can generally only be controlled through manual prediction by experienced employees, thereby controlling the profits of the power plant. This is inefficient and the benefits are uncontrollable.

[0063] Based on this, this embodiment determines the power plant type of the power plant and the power generation influencing factors corresponding to the power plant type, so as to determine the power generation influencing data affecting the power generation of the power plant, and obtains a big data sample of the power generation influencing data accordingly, thereby improving the fit of the constructed intelligent decision-making model. Finally, through the constructed target intelligent decision-making model, an intelligent decision-making plan corresponding to the power plant is generated to control the power generation of the power plant, improve the power generation of the power plant, and increase the power generation revenue.

[0064] In this embodiment, the types of target power plants include but are not limited to: thermal power generation, hydropower generation, photovoltaic power generation, wind power generation and nuclear power, etc. Correspondingly, the power generation influencing factors corresponding to thermal power generation include at least: the fuel input of the combustion furnace, the operating status of the generator set, the switch status of the cooling circuit, etc.; the power generation influencing factors of hydropower generation include at least: water flow and the operating status of the generator set, etc. As for the power generation influencing factors of other types of power plants, this embodiment does not give a specific introduction to them.

[0065] Step S20: Acquire a large data sample of power generation impact data corresponding to the power generation impact factor.

[0066] It should be understood that the power generation impact data may be obtained by various types of structured, semi-structured and unstructured data obtained from RFID radio frequency data, sensor data, social network interaction data, mobile Internet data and the like.

[0067] Furthermore, after obtaining the large data sample of power generation impact data corresponding to the power generation impact factor, the method further includes:

[0068] Determining data characteristics of the big data sample of power generation impact data;

[0069] Based on the conversion strategy corresponding to the data characteristics of each large data sample, the large data sample is converted into target data of a unified category to obtain a target data set to be processed;

[0070] Accordingly, the target intelligent decision-making model is constructed based on the big data sample of the power generation influencing data, including:

[0071] A target intelligent decision-making model is constructed based on the target data set to be processed.

[0072] It should be noted that the data characteristics of power generation influencing data include extremely large indicators, extremely small indicators, intermediate indicators and interval indicators. Among them, extremely large indicators refer to indicators whose larger values ​​indicate greater power generation; extremely small indicators refer to indicators whose smaller values ​​indicate greater power generation; intermediate indicators refer to indicators whose closer to a certain value, greater power generation; and interval indicators refer to indicators whose closer to a certain interval, greater power generation.

[0073] In the field of power generation, it is not just the power generation influencing data that may have different effects on power generation efficiency. For example, for thermal power generation, too little fuel will reduce the speed of the generator set, thereby reducing power generation. However, too much fuel may also lead to incomplete combustion in the combustion chamber, which will also reduce power generation. Therefore, in this embodiment, for power generation influencing data with different data characteristics, the target data of a unified category can be used to reduce the workload and difficulty of subsequent model construction.

[0074] In the specific implementation, big data samples with various data characteristics are processed through forward processing and standardization, so that the obtained big data samples are processed on the same dimension to improve the efficiency of building subsequent models. Among them, the forward processing can be to convert all indicators such as extremely small indicators, intermediate indicators and interval indicators into extremely large indicators.

[0075] Step S30: constructing a target intelligent decision-making model based on the big data sample of the power generation impact data.

[0076] It can be understood that the target intelligent decision-making model is used to generate an intelligent decision-making plan for the target power plant, thereby controlling the input amount of each fuel in the power plant, the flow of power generation raw materials, etc. It can also be used to control the operating status of the generator set, thereby controlling the power generation power of the power plant.

[0077] Step S40: Generate an intelligent decision plan for the target power plant through the target intelligent decision model to control the power generation power of the target power plant.

[0078] Step S50: Controlling the operating state of the target power plant based on the intelligent decision-making solution.

[0079] Since there are peak and valley electricity prices when electricity is connected to the grid, and considering the impact of electricity storage costs on power plant profits, this embodiment only considers controlling the power generation in different time periods to reduce storage costs. That is, when controlling the operating status of the target power plant, this embodiment can be controlled in combination with the peak and valley electricity prices of the local power grid.

[0080] This embodiment determines the power plant type of the power plant and the power generation influencing factors corresponding to the power plant type, thereby determining the power generation influencing data that affects the power generation of the power plant, and correspondingly obtains a big data sample of the power generation influencing data, thereby improving the fit of the constructed intelligent decision-making model. Finally, through the constructed target intelligent decision-making model, an intelligent decision-making plan corresponding to the power plant is generated to control the power generation of the power plant, improve the power generation of the power plant, and increase the power generation revenue, thereby avoiding the technical problem of uncontrollable revenue during the power generation operation of the power plant in the prior art.

[0081] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S40, comprising:

[0082] Step S401: Acquire the current working status and current power generation data of the target power plant.

[0083] Step S402: determining at least one candidate decision solution based on a decision database, the current power generation data, and the current working state, wherein the decision database corresponds to the power plant type of the target power plant.

[0084] Step S403: Evaluate the applicability of each candidate decision solution through the target intelligent decision model to determine the intelligent decision solution of the target power plant from the candidate decision solutions.

[0085] It should be noted that the current working status of the target power plant refers to the operating status of each generator set or power generation equipment in the power plant, such as: generator operating power, rotor speed, etc. The current power generation data refers to the average power generation of the target power plant in the current period, or the average power generation power.

[0086] The candidate decision scheme is the theoretically optimal power generation control strategy. The candidate decision scheme is obtained by networking and then using the decision database corresponding to the power plant type to determine the control scheme that can theoretically increase the power generation corresponding to the current working status of the target power plant and the current power generation data, without considering factors such as the power generation quota, the size of the combustion chamber, and the rated power of the generator set.

[0087] Due to the limited hardware of the target power plant, there may be reasons such as power generation quota, combustion chamber size and rated power of the generator set, which makes it impossible to increase the power generation or power generation according to some theoretical control schemes. Therefore, this embodiment also needs to conduct a suitability assessment on each candidate decision plan to determine the feasibility of each candidate plan.

[0088] Furthermore, the applicability of each candidate decision solution is evaluated by the target intelligent decision model to determine the intelligent decision solution of the target power plant from each candidate decision solution, including:

[0089] Splitting the control actions between the current working state and the candidate decision scheme to obtain at least two target control actions;

[0090] Calculating the continuous control cost of the current working state through the at least two target control actions based on the power generation impact factor;

[0091] Performing a suitability evaluation on the candidate decision scheme based on the continuous control cost corresponding to the continuous control action;

[0092] The candidate decision schemes that pass the applicability evaluation are used as the intelligent decision schemes of the target power plant.

[0093] In the specific implementation, evaluating the applicability of each candidate decision plan means splitting the gap between the operating status of the generator set corresponding to each candidate plan and the current working status into multiple steps, thereby evaluating the feasibility of each step. This can not only reduce the impact on equipment stability caused by adjusting the operating status of each device, but also avoid generator set shutdown caused by hardware inconsistency.

[0094] Furthermore, the applicability evaluation of the candidate decision schemes based on the continuous control costs corresponding to each control action includes:

[0095]

[0096] Among them, c(s t ,s t+1 ) refers to the control cost of adjusting the current working state to the first target control action, c(s t ,s t+1 ) refers to the control cost of adjusting the first target control action to the second target control action, λ is the attenuation factor corresponding to the power plant type, δ is the slack variable, φ(s t ) is a preset evaluation function used to evaluate the benefits of the final operating state of the target power plant.

[0097] This embodiment obtains the current working status and current power generation data of the target power plant; determines at least one candidate decision plan based on a decision database and the current power generation data, wherein the decision database corresponds to the power plant type of the target power plant; and evaluates the applicability of each candidate decision plan through the target intelligent decision model to determine the intelligent decision plan of the target power plant from the candidate decision plans, thereby improving the feasibility of the intelligent decision plan generated by the target intelligent decision model.

[0098] Based on the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 3 , step S50, comprising:

[0099] Step S501: Obtain the peak and valley electricity prices of the local power grid and the power generation quota of the power plant.

[0100] Step S502: modifying the intelligent decision-making plan according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making plan.

[0101] Step S503: Controlling the operating state of the target power plant according to the target intelligent decision-making scheme.

[0102] It should be noted that for some large power plants, there is a minimum power generation requirement for their power generation in each period. Other power generation based on this requirement can be connected to the power grid to obtain profits. However, for some small power plants, there is no minimum power generation requirement. They only need to connect the electricity obtained through various means into the power grid to obtain profits. Therefore, when executing the target intelligent decision-making plan, it is also necessary to consider the limitation of the power generation quota of the power plant, and try to obtain the maximum profit as much as possible while meeting the power generation quota of the power plant.

[0103] Furthermore, the intelligent decision-making scheme is corrected according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making scheme, including:

[0104] Determine the allocation ratio for each time period based on the peak and valley electricity prices of the local power grid and the corresponding impact coefficients;

[0105] Determine the target power generation quota for each time period according to the allocation ratio and the power generation quota of the power plant;

[0106] The intelligent decision-making plan is modified based on the power generation quota to adjust the working status of the target power plant in each time period to obtain a target intelligent decision-making plan.

[0107] In specific implementation, the local power grid peak and valley electricity prices include the power grid peak electricity price and the power grid valley electricity price. The power grid peak electricity price has the highest electricity price and the highest profit; the power grid valley electricity price has the lowest electricity price and the lowest profit.

[0108] If the profit is the highest when selling at the peak price of the local power grid, but storing a large amount of electricity in advance will bring additional storage costs, therefore, it is necessary to reasonably arrange the power generation of the power plant between the peak and trough periods to obtain greater profits. Specifically, by setting a certain influence coefficient for each time period between the peak electricity price and the trough electricity price, the power generation ratio of each time period is determined, so that more electricity can be sold during the peak period and less electricity can be sold during the trough period, thereby obtaining more profits.

[0109] Specifically, taking the peak impact coefficient of 1.5 and the trough impact coefficient of 0.5 as an example, the power generation quota of a thermal power plant is 1.2 billion kWh a year, averaging 100 million kWh per month. It can generate at least 150 million kWh of electricity during the peak period and only 50 million kWh during the trough period, thereby achieving more profits during the peak period of electricity prices and reducing power generation during the trough period, thereby obtaining more profits for the power plant.

[0110] This embodiment obtains the peak-valley electricity prices of the local power grid and the power generation quota of the power plant; modifies the intelligent decision-making plan according to the peak-valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making plan; controls the operating state of the target power plant according to the target intelligent decision-making plan, and further modifies the intelligent decision-making plan generated by the model through the peak-valley electricity prices of the local power grid and the power generation quota of the power plant, thereby improving the power generation revenue of the power plant throughout the year.

[0111] This application also provides an intelligent decision-making device based on a large model, please refer to Figure 4 , the intelligent decision-making device based on the large model includes:

[0112] The determination module 10 is used to determine the power plant type of the target power plant and the power generation impact factor corresponding to the power plant type.

[0113] The acquisition module 20 is used to acquire a large data sample of power generation impact data corresponding to the power generation impact factor.

[0114] The construction module 30 is used to construct a target intelligent decision-making model based on the big data sample of the power generation influencing data.

[0115] The generating module 40 is used to generate an intelligent decision-making plan of the target power plant through the target intelligent decision-making model to control the power generation power of the target power plant.

[0116] The control module 50 is used to control the operating state of the target power plant based on the intelligent decision-making solution.

[0117] This embodiment determines the power plant type of the power plant and the power generation influencing factors corresponding to the power plant type, thereby determining the power generation influencing data that affects the power generation of the power plant, and correspondingly obtains a big data sample of the power generation influencing data, thereby improving the fit of the constructed intelligent decision-making model. Finally, through the constructed target intelligent decision-making model, an intelligent decision-making plan corresponding to the power plant is generated to control the power generation of the power plant, improve the power generation of the power plant, and increase the power generation revenue, thereby avoiding the technical problem of uncontrollable revenue during the power generation operation of the power plant in the prior art.

[0118] In one embodiment, the generation module 40 is also used to obtain the current working status and current power generation data of the target power plant; determine at least one candidate decision plan based on a decision database and the current power generation data, and the decision database corresponds to the power plant type of the target power plant; evaluate the applicability of each candidate decision plan through the target intelligent decision model to determine the intelligent decision plan of the target power plant from the candidate decision plans.

[0119] In one embodiment, the generation module 40 is also used to split the control action between the current working state and the candidate decision scheme to obtain at least two target control actions; calculate the continuous control cost of passing the current working state through the at least two target control actions based on the power generation impact factor; evaluate the applicability of the candidate decision scheme based on the continuous control cost corresponding to the continuous control action; and use the candidate decision scheme that passes the applicability evaluation as the intelligent decision scheme of the target power plant.

[0120] In one embodiment, the generating module 40 is further used to Among them, c(s t ,s t+1 ) refers to the control cost of adjusting the current working state to the first target control action, c(s t ,s t+1 ) refers to the control cost of adjusting the first target control action to the second target control action, λ is the attenuation factor corresponding to the power plant type, δ is the slack variable, φ(s t ) is a preset evaluation function used to evaluate the benefits of the final operating state of the target power plant.

[0121] In one embodiment, the acquisition module 20 is also used to determine the data characteristics of the big data sample of the power generation impact data; based on the conversion strategy corresponding to the data characteristics of each large data sample, the big data sample is converted into assessment data of a unified category to obtain an assessment data set to be processed; accordingly, the target intelligent decision-making model is constructed based on the big data sample of the power generation impact data, including: constructing a target intelligent decision-making model based on the assessment data set to be processed.

[0122] In one embodiment, the control module 50 is also used to obtain the peak and valley electricity prices of the local power grid and the power generation quota of the power plant; modify the intelligent decision-making plan according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making plan; and control the operating status of the target power plant according to the target intelligent decision-making plan.

[0123] In one embodiment, the control module 50 is also used to determine the allocation ratio of each time period based on the peak and valley electricity prices of the local power grid and the corresponding influence coefficient; determine the target power generation quota of each time period according to the allocation ratio and the power generation quota of the power plant; and correct the intelligent decision-making plan based on the power generation quota to adjust the working status of the target power plant in each time period to obtain a target intelligent decision-making plan.

[0124] The present application provides an intelligent decision-making device based on a large model, and the intelligent decision-making device based on a large model includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent decision-making method based on the large model in the above-mentioned embodiment one.

[0125] Reference below Figure 5 , which shows a schematic diagram of the structure of a large-model-based intelligent decision-making device suitable for implementing the embodiment of the present application. The large-model-based intelligent decision-making device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The large model-based intelligent decision-making device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0126] like Figure 5 As shown, the intelligent decision-making device based on the large model may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the intelligent decision-making device based on the large model are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the intelligent decision-making device based on the large model to communicate with other devices wirelessly or by wire to exchange data. Although the diagram shows an intelligent decision-making device based on the large model with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0127] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0128] The intelligent decision-making device based on a large model provided by the present application adopts the intelligent decision-making method based on a large model in the above-mentioned embodiment, which can solve the technical problems of intelligent decision-making based on a large model. Compared with the prior art, the beneficial effects of the intelligent decision-making device based on a large model provided by the present application are the same as the beneficial effects of the intelligent decision-making method based on a large model provided by the above-mentioned embodiment, and the other technical features in the intelligent decision-making device based on a large model are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0129] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0131] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the large model-based intelligent decision-making method in the above-mentioned embodiment.

[0132] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0133] The above-mentioned computer-readable storage medium may be included in the intelligent decision-making device based on the large model; or it may exist independently without being assembled into the intelligent decision-making device based on the large model.

[0134] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the intelligent decision-making device based on the big model, the intelligent decision-making device based on the big model makes: intelligent decision based on the big model.

[0135] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0138] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent decision-making method based on a large model, and can solve the technical problems of intelligent decision-making based on a large model. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intelligent decision-making method based on a large model provided in the above-mentioned embodiment, and will not be repeated here.

[0139] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned large model-based intelligent decision-making method when executed by a processor.

[0140] The computer program product provided in this application can solve the technical problem of intelligent decision-making based on large models. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the intelligent decision-making method based on large models provided in the above embodiments, which will not be repeated here.

[0141] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An intelligent decision-making method based on a large model, characterized in that: The intelligent decision-making method based on the large model includes: Determining a power plant type of a target power plant and a power generation impact factor corresponding to the power plant type; Acquire a large data sample of power generation impact data corresponding to the power generation impact factor; Building a target intelligent decision-making model based on the big data sample of the power generation impact data; Generate an intelligent decision-making plan for the target power plant through the target intelligent decision-making model to control the power generation power of the target power plant; The operating state of the target power plant is controlled based on the intelligent decision-making scheme.

2. The method according to claim 1, characterized in that The generating the intelligent decision-making scheme of the target power plant by using the target intelligent decision-making model includes: Acquiring the current operating status and current power generation data of the target power plant; Determine at least one candidate decision solution based on a decision database, the current power generation data, and the current working state, wherein the decision database corresponds to a power plant type of the target power plant; The applicability of each candidate decision plan is evaluated through the target intelligent decision model to determine the intelligent decision plan of the target power plant from the candidate decision plans.

3. The method according to claim 2, characterized in that The method of evaluating the applicability of each candidate decision solution through the target intelligent decision model to determine the intelligent decision solution of the target power plant from the candidate decision solutions includes: Splitting the control actions between the current working state and the candidate decision scheme to obtain at least two target control actions; Calculating the continuous control cost of the current working state through the at least two target control actions based on the power generation impact factor; Performing a suitability evaluation on the candidate decision scheme based on the continuous control cost corresponding to the continuous control action; The candidate decision schemes that pass the applicability evaluation are used as the intelligent decision schemes of the target power plant.

4. The method according to claim 3, characterized in that The evaluating the applicability of the candidate decision schemes based on the continuous control costs corresponding to each control action includes: Among them, c(s t ,s t+1 ) refers to the control cost of adjusting the current working state to the first target control action, c(s t ,s t+1 ) refers to the control cost of adjusting the first target control action to the second target control action, λ is the attenuation factor corresponding to the power plant type, δ is the slack variable, φ(s t ) is a preset evaluation function used to evaluate the benefits of the final operating state of the target power plant.

5. The method according to claim 1, characterized in that After obtaining the large data sample of power generation impact data corresponding to the power generation impact factor, the method further includes: Determining data characteristics of the big data sample of power generation impact data; Based on the conversion strategy corresponding to the data characteristics of each large data sample, the large data sample is converted into target data of a unified category to obtain a target data set to be processed; Accordingly, the target intelligent decision-making model is constructed based on the big data sample of the power generation influencing data, including: A target intelligent decision-making model is constructed based on the target data set to be processed.

6. The method according to claim 1, characterized in that The controlling the operating state of the target power plant based on the intelligent decision-making scheme includes: Obtain the peak and valley electricity prices of the local power grid and the power generation quota of the power plant; Modifying the intelligent decision-making scheme according to the peak and valley electricity prices of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making scheme; The operating state of the target power plant is controlled according to the target intelligent decision-making scheme.

7. The method according to claim 6, characterized in that The method of amending the intelligent decision-making scheme according to the peak-valley electricity price of the local power grid and the power generation quota of the power plant to obtain a target intelligent decision-making scheme includes: Determine the allocation ratio for each time period based on the peak and valley electricity prices of the local power grid and the corresponding impact coefficients; Determine the target power generation quota for each time period according to the allocation ratio and the power generation quota of the power plant; The intelligent decision-making plan is modified based on the power generation quota to adjust the working status of the target power plant in each time period to obtain a target intelligent decision-making plan.

8. An intelligent decision-making device based on a large model, characterized in that: The intelligent decision-making device based on the large model includes: A determination module, used to determine the power plant type of the target power plant and the power generation impact factor corresponding to the power plant type; An acquisition module, used to acquire a large data sample of power generation impact data corresponding to the power generation impact factor; A building module, used for building a target intelligent decision-making model based on the big data sample of the power generation impact data; A generation module, used to generate an intelligent decision-making plan of the target power plant through the target intelligent decision-making model to control the power generation power of the target power plant; A control module is used to control the operating state of the target power plant based on the intelligent decision-making solution.

9. An intelligent decision-making device based on a large model, characterized in that: The big model-based intelligent decision-making device includes: a memory, a processor, and a big model-based intelligent decision-making program stored in the memory and executable on the processor, wherein the big model-based intelligent decision-making program is configured to implement the steps of the big model-based intelligent decision-making method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a large-model-based intelligent decision-making program, which, when executed by a processor, implements the steps of the large-model-based intelligent decision-making method as described in any one of claims 1 to 7.

Images