Method and apparatus for generating production task allocation for a gas power plant

Abstract

This invention relates to a method and apparatus for generating production tasks for gas-fired power plants. The method includes constructing a daily-dimensional sample library; estimating the daily production tasks for the following year by combining the daily-dimensional sample library with the task plan for the following year; determining the boundary range of the daily-dimensional sample library based on daily power generation, daily heat supply, average daily ambient temperature, and humidity, determining a profit optimization logic, and obtaining the optimal profit value; determining the daily-dimensional production tasks corresponding to historical days in the following year; adjusting the daily-dimensional production tasks for the following year to obtain the optimal daily-dimensional production tasks; and calculating the optimal monthly-dimensional production tasks based on the optimal daily-dimensional production tasks. This invention addresses the problem that manual scheduling of production tasks cannot meet the requirements of dispatching and operation and has low economic efficiency by strengthening the refined management of power generation and heat supply rhythms and accurate pre-prediction, thereby enabling better allocation of annual, monthly, and daily power generation and heat supply tasks for gas-fired power plants.

Description

Technical Field

[0001] This invention belongs to the field of power system technology, specifically relating to a method and apparatus for generating production task allocation for gas-fired power plants. Background Technology

[0002] Gas-fired combined cycle (GC) units are widely used due to their high energy efficiency and environmental friendliness. However, the maximum power load of GC units is significantly influenced by environmental factors, including peak heating seasons in winter and high power loads in summer, compounded by power peak shaving issues. Simultaneously, the economic efficiency of generator operation must be considered, making the planning of power generation and heating supply highly challenging, and the annual production task allocation schedule for each power plant difficult to control. Previously, power plants often used experienced technicians to manually allocate annual and monthly power generation and heating supply for GC units, with little consideration given to the actual economic benefits of unit operation. The focus was primarily on ensuring grid safety during maximum operation, relying on past experience for power generation and heating supply data, and comparing results through visual observation and manual data processing. This manual calculation method is not only labor-intensive but also requires frequent readjustment whenever the strategy is slightly adjusted, resulting in extremely low efficiency.

[0003] In related technologies, some gas-fired power plants utilize intelligent software systems, such as production management planning and statistical analysis systems, to track power generation and heating in real time based on the unified organization of data ledgers and reports from various departments. These systems allow for manual adjustments to future power generation and heating plans, thus allocating production tasks for the gas-fired power plant. However, while these technologies collect and input information from various departments and utilize extensive report data statistics and analysis to reduce manual workload and improve the accuracy of statistical data, thereby enhancing the plant's automation level, they are still post-hoc statistical analyses relying solely on human experience. They cannot scientifically and accurately predict future production task allocation for gas-fired power plants, and therefore cannot schedule annual, monthly, or daily power generation and heating tasks for the plant while meeting dispatching requirements and achieving optimal economic benefits. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and provide a method and apparatus for generating production tasks for gas-fired power plants, so as to solve the problem that the prior art cannot arrange power generation and heat supply tasks for gas-fired power plants while meeting the scheduling and operation requirements and achieving optimal economic benefits.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for generating production task allocation for gas-fired power plants, comprising:

[0006] Based on historical data of equivalent generating units, a daily sample library is constructed; the historical data includes daily power generation, daily heat supply, daily average ambient temperature, humidity, and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit.

[0007] Based on the task allocation ratio of the previous year and the task plan for the next year, estimate the daily production task of the equivalent unit for the next year.

[0008] The boundary range of the daily dimension sample library is determined based on the daily power generation, daily heat supply, daily average ambient temperature and humidity. Based on the daily profit parameter and the boundary range, the profit optimization logic is determined from the daily dimension sample library to obtain the optimal profit value.

[0009] Based on the historical daily production tasks corresponding to the optimal profit value, determine the daily production tasks corresponding to the historical day in the following year;

[0010] Based on the optimal power generation and heat supply for the day, the production tasks for the next day are redistributed until the production tasks based on the optimal profit allocation for each day of the year are completed.

[0011] Calculate the optimal monthly production task based on the optimal daily production task.

[0012] Furthermore, the historical dimension data also includes:

[0013] The equivalent unit's natural gas consumption, water consumption, ammonia consumption, purchased electricity, operating conditions, lower heating value of gas, power generation consumption, comprehensive plant power consumption rate, heat price, gas price, electricity price, average load factor, and average load.

[0014] Furthermore, determining the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature, and humidity includes:

[0015] Set the filtering range for the power generation, the daily heat supply, the daily average ambient temperature and humidity, and determine the filtering range as the boundary range of the daily dimension sample library.

[0016] Furthermore, the variable cost per kilowatt-hour includes the variable cost per kilowatt-hour for heating and the variable cost per kilowatt-hour for no heating; the marginal profit includes the marginal profit for heating and the marginal profit for no heating; the step of determining the profit optimization logic from the daily dimension sample library based on the daily profit parameters and boundary range to obtain the optimal profit value includes:

[0017] Within the boundary range, find the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply days in the daily dimension sample library.

[0018] The optimization logic is determined by finding the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply, thus obtaining the optimal value.

[0019] Furthermore, determining the daily-dimensional production task corresponding to the historical day in the following year based on the historical daily production task corresponding to the optimal profit value includes:

[0020] Determine the historical day corresponding to the optimal value, determine the daily dimension production task corresponding to the historical day in the next year, and determine the data of each dimension corresponding to the historical day.

[0021] Furthermore, based on the optimal power generation and heat supply for the day, the production tasks for the next day are redistributed to obtain the optimal daily production tasks, until the production tasks allocated based on the optimal profit distribution for each day of the year are completed, including:

[0022] After determining the optimal power generation and heat supply for the day, determine the remaining power generation and heat supply for the year.

[0023] Based on the remaining power generation and heat supply, and the daily production task allocation ratio of the previous year, the production task of the next day in the next year is redistributed to determine the historical day corresponding to the optimal value of the next day, so as to obtain the optimal daily production task, until the production task of each day of the year based on the optimal profit allocation is completed.

[0024] Furthermore, it also includes:

[0025] Compare the actual daily production tasks with the optimal daily production tasks to identify the differences.

[0026] The operation and scheduling of the power system are adjusted based on the aforementioned difference data.

[0027] Furthermore, the screening range is ±2% for power generation, ±2% for heat supply, ±2% for ambient temperature, and ±5% for ambient humidity.

[0028] This application provides a generation device for allocating production tasks in a gas-fired power plant, comprising:

[0029] A construction module is used to build a daily dimension sample library based on historical dimension data of equivalent generating units; the historical dimension data includes daily power generation, daily heat supply, daily average ambient temperature, humidity and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit.

[0030] The estimation module is used to estimate the daily production allocation tasks of the equivalent unit in the next year by combining the task allocation ratio of the previous year and the task plan for the next year.

[0031] The optimization module is used to determine the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature and humidity, and to determine the profit optimization logic from the daily dimension sample library based on the daily profit parameter and the boundary range to obtain the optimal profit value.

[0032] The determination module is used to determine the daily-dimensional production tasks and data of each dimension corresponding to the historical day corresponding to the optimal profit value in the following year.

[0033] The iteration module is used to redistribute the production tasks for the next day based on the optimal power generation and heat supply for the current day, until the production tasks based on the optimal profit allocation for each day of the year are completed.

[0034] The calculation module is used to calculate the optimal monthly production task based on the optimal daily production task.

[0035] The beneficial effects that can be achieved by adopting the above technical solution in this invention include:

[0036] This invention provides a method and apparatus for generating production tasks for gas-fired power plants. By strengthening the refined management of power generation and heating rhythms and making accurate predictions in advance, this application solves the problem that manual scheduling of production tasks cannot meet the requirements of dispatching and operation and has low economic benefits. This allows for better scheduling of annual, monthly and daily power generation and heating tasks for gas-fired power plants. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram illustrating the steps of the method for generating production task allocation in a gas-fired power plant according to the present invention.

[0039] Figure 2 This is a schematic diagram of the generation device for allocating production tasks in a gas-fired power plant according to the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0041] This application, based on the annual power generation and heating plans issued by the dispatch center for the equivalent generating units, aims to maximize the annual profitability and achieve the daily power generation and heating production targets for the gas-fired power plant. It also assists the power plant in rationally arranging fuel supply and shutdown plans (including maintenance and testing).

[0042] The following describes, with reference to the accompanying drawings, a specific method and apparatus for generating production tasks for gas-fired power plants, as provided in an embodiment of this application.

[0043] like Figure 1 As shown in the embodiments of this application, the method for generating production tasks for gas-fired power plants includes:

[0044] S101, Based on historical dimension data of equivalent generating units, a daily dimension sample library is constructed; the historical dimension data includes daily power generation, daily heat supply, daily average ambient temperature, humidity, and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit;

[0045] Specifically, this application connects with the plant's SIS system to store the equivalent unit's historical daily power generation, heat supply, natural gas consumption, water consumption, ammonia consumption, purchased electricity, daily average ambient temperature, humidity, operating conditions, lower heating value of gas, power consumption, comprehensive plant power consumption rate, heat price, gas price, electricity price, average load factor, average load, variable cost per kilowatt-hour (including heat supply), variable cost per kilowatt-hour (excluding heat supply), marginal profit (including heat supply), and marginal profit (excluding heat supply).

[0046] The daily profit parameters include:

[0047] Variable cost per kilowatt-hour (including heating) = Gas cost per kilowatt-hour (including heating) + Water cost per kilowatt-hour + Ammonia cost per kilowatt-hour + Cost of purchased electricity per kilowatt-hour;

[0048] Variable cost per kilowatt-hour (excluding heating) = Gas cost per kilowatt-hour (excluding heating) + Water cost per kilowatt-hour + Ammonia cost per kilowatt-hour + Cost of purchased electricity per kilowatt-hour;

[0049] Marginal profit (including heating) = (Electricity revenue + Heating revenue) / Electricity generation - Variable cost per kilowatt-hour (including heating);

[0050] Marginal profit (excluding heating) = (Electricity revenue + Heating revenue) / Electricity generation - Variable cost per kilowatt-hour (excluding heating).

[0051] S102. Based on the task allocation ratio of the previous year and the task plan for the next year, estimate the daily production task of the equivalent unit for the next year.

[0052] Specifically, this application estimates the daily power generation and heating tasks of the equivalent generating units based on historical daily power generation and heating data of the power plant, combined with the planned power generation and heating tasks for the entire year (the total number assigned by the dispatch) and maintenance plans.

[0053] S103, determine the boundary range of the daily dimension sample library based on the daily power generation and daily heat supply, and determine the profit optimization logic from the daily dimension sample library based on the daily profit parameter and the boundary range to obtain the optimal profit value;

[0054] In some embodiments, determining the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature, and humidity includes:

[0055] Set the filtering range for the power generation, the daily heat supply, the daily average ambient temperature and humidity, and determine the filtering range as the boundary range of the daily dimension sample library.

[0056] In some embodiments, the variable cost per kilowatt-hour includes the variable cost per kilowatt-hour for heating and the variable cost per kilowatt-hour for no heating; the marginal profit includes the marginal profit for heating and the marginal profit for no heating; the step of determining the profit optimization logic from the daily dimension sample library based on the daily profit parameter and boundary range to obtain the optimal profit value includes:

[0057] Within the boundary range, find the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply days in the daily dimension sample library.

[0058] The optimization logic is determined by finding the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply, thus obtaining the optimal value.

[0059] Understandably, this application defines the sample library screening boundary range (power generation ±2%, heat supply ±2%, ambient temperature ±2%, ambient humidity ±2%) based on the daily power generation and heat supply decomposed from the daily dimension sample library. Within the screening range, the minimum daily variable cost per kilowatt-hour (including heat supply), the minimum daily variable cost per kilowatt-hour (excluding heat supply), the maximum daily marginal profit (including heat supply), and the maximum daily marginal profit (excluding heat supply) are searched in the sample library. Depending on the actual situation, among the above four values, an optimization logic can be manually selected to obtain the optimal value.

[0060] S104, Based on the historical daily production task corresponding to the optimal profit value, determine the daily dimension production task corresponding to the historical day in the next year;

[0061] In some embodiments, determining the daily-dimensional production task corresponding to the historical day in the following year based on the historical daily production task corresponding to the optimal profit value includes:

[0062] Determine the historical day corresponding to the optimal value, determine the daily dimension production task corresponding to the historical day in the next year, and determine the data of each dimension corresponding to the historical day.

[0063] Specifically, the optimal values ​​are obtained by identifying the data for a specific historical day across various dimensions: power generation, heat supply, natural gas consumption, water consumption, ammonia consumption, purchased electricity, average daily ambient temperature, humidity, operating conditions, lower heating value of natural gas, power consumption, overall plant power consumption rate, heat price, gas price, electricity price, and average load factor. The aforementioned power generation and heat supply represent the daily production tasks based on the optimal allocation of profits.

[0064] S105, based on the optimal power generation and heat supply of the day, redistribute the production tasks for the next day until the production tasks based on the optimal profit allocation for each day of the year are completed.

[0065] In some embodiments, the step of redistributing the production tasks for the next day based on the actual power generation of the day to obtain the optimal production tasks for the next day, until the production tasks based on the optimal profit allocation for each day of the year are completed, includes:

[0066] After determining the optimal power generation and heat supply for the day, determine the remaining power generation and heat supply for the year.

[0067] Based on the remaining power generation and heat supply, and the daily production task allocation ratio of the previous year, the production task of the next day in the next year is redistributed to determine the historical day corresponding to the optimal value of the next day, so as to obtain the optimal daily production task, until the production task of each day of the year based on the optimal profit allocation is completed.

[0068] Specifically, after obtaining the daily production tasks corresponding to the historical days, based on the principle that the total amount of power generation and heat supply allocated throughout the year remains unchanged, the remaining power generation and heat supply for the year are iteratively adjusted according to the optimal power generation and heat supply for the day. Steps S102-S105 are repeated until the production tasks allocated based on the optimal profit allocation for each day of the year are completed.

[0069] S106, Calculate the optimal monthly production task based on the optimal daily production task.

[0070] After obtaining the optimal daily production task, the optimal daily production task allocation plan is accumulated and allocated to the monthly level to form the optimal monthly decomposition curve.

[0071] In some embodiments, it also includes:

[0072] Compare the actual daily production tasks with the optimal daily production tasks to identify the differences.

[0073] The operation and scheduling of the power system are adjusted based on the aforementioned difference data.

[0074] Specifically, by comparing with actual values, the differences between historical optimal parameter indicators and actual operating parameters are identified, and the difference data is provided to guide the operation of the power system.

[0075] The working principle of the method for generating production tasks for gas-fired power plants is as follows: A daily dimension sample library is constructed based on historical dimension data of the equivalent generating units. This historical dimension data includes daily power generation, daily heat supply, average daily ambient temperature, humidity, and daily profit parameters. The daily profit parameters include variable cost per kilowatt-hour and marginal profit. Combining the daily dimension sample library with the next year's task plan, the daily production tasks allocated to the equivalent generating units for the next year are estimated. The boundary range of the daily dimension sample library is determined based on the daily power generation and daily heat supply. Based on the daily profit parameters and the boundary range, a profit optimization logic is determined from the daily dimension sample library to obtain the optimal profit value. Based on the historical day corresponding to the optimal profit value and the daily production tasks allocated for the next year, the daily dimension production tasks corresponding to the historical day in the next year are determined. The daily dimension production tasks for the next year are adjusted based on the actual power generation of the day to obtain the optimal daily dimension production tasks. Finally, the optimal monthly dimension production tasks are calculated based on the optimal daily dimension production tasks.

[0076] like Figure 2 As shown in the figure, this application provides a generation device for allocating production tasks in a gas-fired power plant, comprising:

[0077] Module 201 is used to construct a daily dimension sample library based on historical dimension data of equivalent generating units; the historical dimension data includes daily power generation, daily heat supply, daily average ambient temperature, humidity and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit.

[0078] The estimation module 202 is used to estimate the daily production allocation tasks of the equivalent unit in the next year by combining the task allocation ratio of the previous year and the task plan for the next year.

[0079] The optimization module 203 is used to determine the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature and humidity, and to determine the profit optimization logic from the daily dimension sample library based on the daily profit parameter and the boundary range to obtain the optimal profit value.

[0080] The determination module 204 is used to determine the daily production tasks and data of each dimension corresponding to the historical day corresponding to the optimal profit value in the next year.

[0081] Iteration module 205 is used to redistribute the production tasks for the next day based on the optimal power generation and heat supply of the day, until the production tasks based on the optimal profit allocation for each day of the year are completed.

[0082] The calculation module 206 is used to calculate the optimal monthly production task based on the optimal daily production task.

[0083] The working principle of the generation device for production task allocation in gas-fired power plants provided in this application is as follows: A construction module 201 constructs a daily dimension sample library based on historical dimension data of the equivalent unit; the historical dimension data includes daily power generation, daily heat supply, daily average ambient temperature, humidity, and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit; an estimation module 202 estimates the daily allocation production tasks for the equivalent unit in the following year based on the task allocation ratio of the previous year and the task plan for the following year; an optimization module 203 estimates the daily allocation production tasks for the equivalent unit in the following year based on the task allocation ratio of the previous year and the task plan for the following year; a determination module 204 determines the daily dimension production tasks and data for each dimension corresponding to the historical day corresponding to the optimal profit value in the following year; an iteration module 205 redistributes the daily dimension production tasks based on the optimal power generation and heat supply of the day until the production tasks based on the optimal profit allocation for each day of the year are completed; and a calculation module 206 calculates the optimal monthly dimension production tasks based on the optimal daily dimension production tasks.

[0084] In summary, this invention provides a method and apparatus for generating production tasks for gas-fired power plants. The method includes: constructing a daily dimension sample library based on historical dimension data; estimating the daily production tasks for the following year by combining the daily dimension sample library with the task plan for the following year; determining the boundary range of the daily dimension sample library based on daily power generation, daily heat supply, average daily ambient temperature, and humidity, determining the profit optimization logic, and obtaining the optimal profit value; determining the daily dimension production tasks corresponding to historical days in the following year; redistributing the daily dimension production tasks for the following year until the production tasks for each day of the year are completed based on the optimal profit allocation; and calculating the optimal monthly dimension production tasks based on the optimal daily dimension production tasks. This invention addresses the problem that manual scheduling of production tasks cannot meet the requirements of dispatching and operation and has low economic efficiency by strengthening the refined management of power generation and heat supply rhythms and accurate pre-prediction, thereby enabling better scheduling of annual, monthly, and daily power generation and heat supply tasks for gas-fired power plants.

[0085] It is understood that the method embodiments provided above correspond to the device embodiments described above, and the specific details can be referred to each other, which will not be repeated here.

[0086] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0087] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction methods implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for generating a production task allocation for a gas power plant, characterized in that, include: Based on historical data of equivalent generating units, a daily sample library is constructed; the historical data includes daily power generation, daily heat supply, daily average ambient temperature, humidity, and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit. Based on the task allocation ratio of the previous year and the task plan for the next year, estimate the daily production task of the equivalent unit for the next year. The boundary range of the daily dimension sample library is determined based on the daily power generation, daily heat supply, daily average ambient temperature and humidity. Based on the daily profit parameter and the boundary range, the profit optimization logic is determined from the daily dimension sample library to obtain the optimal profit value. Based on the historical daily production tasks corresponding to the optimal profit value, determine the daily production tasks corresponding to the historical day in the following year; Based on the optimal power generation and heat supply for the day, the production tasks for the next day are redistributed until the production tasks based on the optimal profit allocation for each day of the year are completed. Calculate the optimal monthly production task based on the optimal daily production task. Determining the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature, and humidity includes: The filtering ranges for the power generation, daily heat supply, daily average ambient temperature, and humidity are set, and these filtering ranges are defined as the boundary ranges of the daily dimension sample library; The variable cost per kilowatt-hour includes the variable cost per kilowatt-hour for heating and the variable cost per kilowatt-hour for no heating. The marginal profit includes the marginal profit from heating and the marginal profit from not heating; The step of determining the profit optimization logic from the daily dimension sample library based on the daily profit parameters and boundary range to obtain the optimal profit value includes: Within the boundary range, find the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply days in the daily dimension sample library. The optimization logic is determined by finding the minimum daily variable cost of electricity for heating supply, the minimum daily variable cost of electricity for no heating supply, the maximum daily marginal profit for heating supply, and the maximum marginal profit for no heating supply, thus obtaining the optimal value. The step of determining the daily-dimensional production task corresponding to the historical day in the following year based on the historical daily production task corresponding to the optimal profit value includes: Determine the historical day corresponding to the optimal value, determine the daily dimension production task corresponding to the historical day in the following year, and determine the data for each dimension corresponding to the historical day; The process of redistributing production tasks for the next day based on the optimal power generation and heat supply for the current day to obtain the optimal daily production tasks continues until the production tasks allocated based on the optimal profit distribution for each day of the year are completed. This includes: After determining the optimal power generation and heat supply for the day, determine the remaining power generation and heat supply for the year. Based on the remaining power generation and heat supply, and according to the daily production task allocation ratio of the previous year, the production tasks for the next day of the following year are redistributed to determine the historical day corresponding to the optimal value of the next day, thus obtaining the optimal daily production task, until the production tasks for each day of the year based on the optimal profit allocation are completed; The screening range is ±2% for power generation, ±2% for heat supply, ±2% for ambient temperature, and ±5% for ambient humidity.

2. The method of claim 1, wherein, The historical dimension data also includes: The equivalent unit's natural gas consumption, water consumption, ammonia consumption, purchased electricity, operating conditions, lower heating value of gas, power generation consumption, comprehensive plant power consumption rate, heat price, gas price, electricity price, average load factor, and average load.

3. The method of claim 1, wherein, Also includes: Compare the actual daily production tasks with the optimal daily production tasks to identify the differences. The operation and scheduling of the power system are adjusted based on the aforementioned difference data.

4. A generating device for production task allocation of a gas power plant, applied to the generating method for production task allocation of a gas power plant in any one of claims 1-3, characterized in that, include: A construction module is used to build a daily dimension sample library based on historical dimension data of equivalent generating units; the historical dimension data includes daily power generation, daily heat supply, daily average ambient temperature, humidity and daily profit parameters; the daily profit parameters include variable cost per kilowatt-hour and marginal profit. The estimation module is used to estimate the daily production allocation tasks of the equivalent unit in the next year by combining the task allocation ratio of the previous year and the task plan for the next year. The optimization module is used to determine the boundary range of the daily dimension sample library based on the daily power generation, daily heat supply, daily average ambient temperature and humidity, and to determine the profit optimization logic from the daily dimension sample library based on the daily profit parameter and the boundary range to obtain the optimal profit value. The determination module is used to determine the daily-dimensional production tasks and data of each dimension corresponding to the historical day corresponding to the optimal profit value in the following year. The iteration module is used to redistribute the production tasks for the next day based on the optimal power generation and heat supply for the current day, until the production tasks based on the optimal profit allocation for each day of the year are completed. The calculation module is used to calculate the optimal monthly production task based on the optimal daily production task.

Images