Big data algorithm-based header system unit heat and power load distribution method, system and equipment and medium

Abstract

The invention discloses a header system unit thermoelectric load distribution method, system and device based on a big data algorithm and a medium, and relates to the technical field of thermoelectric load distribution, and the method comprises the steps: determining a steam turbine type, and selecting a mathematical model according to the steam turbine type; after related parameters are obtained according to a steam turbine type analysis mechanism, data of the related parameters are exported from an SIS system, and the exported data are historical data of one year; cleaning the exported data to obtain historical data of a stable working condition; on the basis of the historical data of the stable working condition, a steam consumption characteristic curve of each steam turbine of the header system heat supply unit is fitted; and analyzing the steam consumption characteristic curve, carrying out mathematical modeling by adopting a linear programming method, and solving the model to obtain an optimal distribution scheme. According to the method, optimization recommendation can be carried out in real time according to the heat load and the electric load of the header unit, and the coal consumption reduction degree can be obtained according to the obtained optimization result through a big data algorithm and a mathematical modeling method.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power load distribution, and in particular to a method and system for distributing thermal power load of a main control unit based on a big data algorithm. Background Art

[0002] Thermal power plants determine their production tasks according to the heat and electricity required by users. Seasonal changes or changes in actual production will lead to changes in user demand, so the production tasks of thermal power plants must also be changed accordingly. In different adjustment processes, on the basis of meeting safety and reliability, there must be an optimal allocation result for multiple units to minimize the energy consumption of the entire plant. The purpose of optimizing the distribution of thermal power loads between main pipe heating units is to find the best load distribution plan in different adjustment plans. To ensure the needs of production and life, and on the basis of safe and reliable operation of the units, the coal consumption of the entire plant is minimized.

[0003] The problems faced by the optimal distribution of thermal and electric loads of main tube heating units are:

[0004] Economic indicators: Currently, there is no plant-wide indicator that can fully measure the economic benefits of thermal power plants, due to the interaction between the working fluid flow and heat of the main pipe heating unit. At present, the solution to this problem is to use the coexistence of plant-wide economic indicators and sub-item indicators to measure its economic efficiency; the actual economic efficiency of the heating unit is the main basis for the power plant to optimize the distribution of thermal power load.

[0005] Optimization method: This is the main problem faced by the mother tube heating unit, and it is also the main research direction of many scholars. Due to some shortcomings of the optimization algorithm, the result obtained is not the true optimal solution. This problem can be improved by improving the method, so the main research direction at home and abroad is how to improve the optimization algorithm.

[0006] Traditional optimization methods: efficiency method and equal incremental rate method.

[0007] Efficiency method: This method is based on the efficiency of the unit. First, the efficiency of each unit is obtained, and then the unit load is distributed according to the efficiency. Its advantages are simplicity and ease of operation, and less calculation, but the actual factor determining the optimal distribution of unit load is not the efficiency of the unit, but the rate of change of unit consumption. Therefore, it is difficult to find the optimal solution in practical applications and cannot meet the requirements of load optimization distribution. Therefore, this method is rarely used at present. Equal incremental rate method: At present, this method is one of the main methods for realizing economic dispatch of electricity. In the optimization of unit load, this method adopts the extreme value theory, which is simple and effective in actual optimization operation. However, the principle of this method is based on classical variational calculus, so there are strict requirements on the optimization objective function in the optimization, which must be a monotonically increasing convex function, and the actual unit consumption characteristic curve may not meet the conditions, resulting in a great impact on the accuracy of the optimization result.

[0008] The thermal power load optimization under the CS client architecture is no longer suitable for the timeliness and effectiveness of data optimization required by current customers. Since the CS architecture is basically an offline application, it cannot be timely. Most of the time, it can only be considered that the data of several working conditions in the same time period are input, and the optimization suggestions corresponding to a certain moment in the past are finally displayed after calculation and analysis; the second is to distribute heat and electricity economically based on the efficiency. It is impossible to analyze based on a large amount of historical data. It can only roughly estimate that more loads are given to those with high efficiency and less loads are given to those with low efficiency. In this way, the extreme value cannot be obtained at all, and the effectiveness of the product cannot be achieved. Therefore, a set of mature BS architecture platform software is needed as the basic platform. From data collection, forwarding, storage, calculation and analysis, data mining, and application display, an integrated platform software is required to achieve.

[0009] The present invention adopts a linear programming method to develop a set of allocation optimization methods based on the BS architecture. Summary of the invention

[0010] In view of the above-mentioned problems, the present invention is proposed.

[0011] Therefore, the problem to be solved by the present invention is that it is difficult to find the optimal solution in practical applications with traditional optimization methods, and the requirements for load optimization distribution cannot be met; the thermal power load optimization under the CS client architecture is no longer suitable for current customers' requirements for the timeliness and effectiveness of data optimization.

[0012] To solve the above technical problems, the present invention provides the following technical solutions: a method for distributing thermal power loads of a busbar heating unit based on a big data algorithm, comprising: determining the type of steam turbine and selecting a mathematical model according to the type of steam turbine; after obtaining relevant parameters according to the steam turbine type analysis mechanism, exporting the data of the relevant parameters from the SIS system, wherein the exported data is historical data for one year; cleaning the exported data to obtain historical data of stable operating conditions; fitting the steam consumption characteristic curve of each steam turbine of the busbar heating unit based on the historical data of stable operating conditions; analyzing the steam consumption characteristic curve, using linear programming method for mathematical modeling, and solving the model to obtain the optimal distribution plan.

[0013] As a preferred solution of the method for distributing thermal and electric loads of the main pipe unit based on the big data algorithm described in the present invention, the types of steam turbines include pure condensing, back pressure, extraction condensing and double extraction units.

[0014] As a preferred solution of the method for distributing thermal and electric loads of a main tube unit based on a big data algorithm according to the present invention, wherein: the mathematical model selected according to the type of steam turbine includes: the mathematical model of the pure condensing type is expressed as: , in, Expressed as the unit's new steam volume, Expressed as the electrical power of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the pure condensing unit. It is expressed as the no-load steam consumption of the main steam of the pure condensing unit; the mathematical model of the back pressure type is expressed as, , , in, Expressed as the extraction steam heat load of the unit, It is expressed as the slight increase rate of power generation steam consumption of the back pressure unit related main steam, It is expressed as the no-load steam consumption of the main steam related to the back pressure unit; It is expressed as the slight increase rate of steam consumption for power generation related to the extraction of steam from the back pressure unit. Expressed as the no-load steam consumption of the extraction steam related to the back pressure unit.

[0015] As a preferred solution of the method for distributing thermal and electric loads of main pipe units based on big data algorithm described in the present invention, wherein: the mathematical model selected according to the type of steam turbine also includes: the mathematical model of the extraction-condensing type is expressed as: , in, Expressed as the total steam consumption of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the single extraction unit. It is expressed as the slight increase rate of extraction steam consumption of main steam related to single extraction unit; It is expressed as the no-load steam consumption of the main steam of the single-extraction unit; the mathematical model of the double-extraction unit is expressed as, , in, Expressed as the total heat consumption of the unit, It represents the electrical load borne by the unit. Expressed as the heat load of the high-pressure steam extraction port, Expressed as the heat load of the low-pressure steam extraction port, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the double extraction unit. It is expressed as the slight increase rate of production extraction steam consumption of main steam related to double extraction units; It is expressed as the slight increase rate of heating extraction steam consumption of the main steam of the double extraction unit. It is expressed as the no-load steam consumption of the main steam related to the double-extraction unit.

[0016] As a preferred solution of the method for distributing thermal and electric loads of bus control units based on big data algorithm described in the present invention, the analysis of the steam consumption characteristic curve includes, for the best value of the steam consumption characteristic coefficient of the corresponding steam turbine type, writing the residual square sum formula based on the data value of the steam consumption characteristic curve as follows: , in, Expressed as the residual sum of squares, is the total number of samples, Expressed as actual value, Denote the dependent variable as the predicted value, Expressed as the unknown quantity; the partial derivative of each unknown quantity is expressed as,

[0017] Minimize the residual sum of squares and set the partial derivatives equal to 0. The resulting rectangular matrix is ​​as follows. Solving it will yield the values ​​of each unknown quantity: .

[0018] As a preferred solution of the method for distributing thermal power load of the main control unit based on the big data algorithm described in the present invention, the analysis of the steam consumption characteristic curve also includes using a close function to measure the closeness of the regression linear equation obtained by the least squares method and the observed data. The close function It is expressed as, , , in, Expressed as the number of variables, Represented as actual value; when When , it means that the relevant equation has a high reference value, that is, the fitted function curve has high reliability and meets the function requirements of linear programming; on the contrary, when When , it indicates that the reference value is low, that is, the reliability of the fitted function curve is low and does not meet the function requirements of linear programming.

[0019] Another object of the present invention is to provide a main tube unit thermal power load distribution system based on a big data algorithm, which can optimize the distribution of the thermal power load of the main tube unit.

[0020] As a preferred solution of the main control unit thermal power load distribution system based on big data algorithm described in the present invention, it includes a real-time data acquisition module for collecting real-time production data; a real-time data storage module for data storage; and a SIS function module for retrieving data in the real-time data storage module for real-time analysis.

[0021] As a preferred solution of the main control unit thermal power load distribution system based on big data algorithm described in the present invention, the real-time data acquisition module collects real-time production data from DCS, ECS, chemical water PLC, and SCADA production control systems through a gateway machine, and integrates the process data originally from scattered and independent sources and unrelated to each other into a unified database in chronological order by building a plant-level process data platform; the SIS function module reads a large amount of historical data from the real-time data storage module, performs big data analysis including data cleaning and emptying, deeply mines data characteristics, and calculates extreme values ​​in real time, and finally displays the data on the platform, pushes real-time data optimization suggestions to on-site operators.

[0022] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for distributing thermal power loads of a main control unit based on a big data algorithm as described above are implemented.

[0023] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for distributing thermal power loads of a main control unit based on a big data algorithm as described above.

[0024] The beneficial effect of the present invention is that compared with the traditional off-line optimization method, the present method can make optimization recommendations in real time based on the two quality energy uses of the heat load and the electric load of the main control unit.

[0025] Through big data algorithms and mathematical modeling methods, the degree of reduction in coal consumption can be determined based on the optimization results.

[0026] By displaying on the front-end page, comparing the data before and after optimization, and comparing the trends, we can more clearly analyze the gap between the current or historical optimization and provide guidance to operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0028] Figure 1 This is a flow chart of the method for allocating thermal power loads of the main control unit based on the big data algorithm in Example 1.

[0029] Figure 2 It is a line graph comparing the method of the present invention for the method for distributing thermal power loads of the main control unit based on the big data algorithm in Example 2 with the genetic algorithm and the particle swarm algorithm. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] Example 1

[0033] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a method for distributing thermal power loads of a main control unit based on a big data algorithm, including: Figure 1 As shown:

[0034] S1. Optimization of turbine side load.

[0035] First, we need to analyze the steam turbine type clearly. Different steam turbine types have different mathematical models and require different related measurement point IDs. Steam turbine types can be mainly divided into pure condensing, back pressure, extraction condensing and double extraction units. Select the mathematical model according to the type of steam turbine on site.

[0036] The purely condensed mathematical model is expressed as: , in, Expressed as the unit's new steam volume, Expressed as the electrical power of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the pure condensing unit. It is expressed as the no-load steam consumption of the main steam related to the pure condensing unit.

[0037] The mathematical model of back pressure is expressed as: , , in, Expressed as the extraction steam heat load of the unit, It is expressed as the slight increase rate of power generation steam consumption of the back pressure unit related main steam, It is expressed as the no-load steam consumption of the main steam related to the back pressure unit; It is expressed as the slight increase rate of steam consumption for power generation related to the extraction of steam from the back pressure unit. Expressed as the no-load steam consumption of the extraction steam related to the back pressure unit.

[0038] The mathematical model of the extraction condensation is expressed as: , in, Expressed as the total steam consumption of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the single extraction unit. It is expressed as the slight increase rate of extraction steam consumption of main steam related to single extraction unit; It is expressed as the no-load steam consumption of the main steam related to the single extraction unit.

[0039] The mathematical model of the double extraction unit is expressed as: , in, Expressed as the total heat consumption of the unit, It represents the electrical load borne by the unit. Expressed as the heat load of the high-pressure steam extraction port, Expressed as the heat load of the low-pressure steam extraction port, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the double extraction unit. It is expressed as the slight increase rate of production extraction steam consumption of main steam related to double extraction units; It is expressed as the slight increase rate of heating extraction steam consumption of the main steam of the double extraction unit. It is expressed as the no-load steam consumption of the main steam related to the double-extraction unit.

[0040] S2. Mechanism analysis: Analyze the mechanism according to the turbine type and obtain relevant parameters.

[0041] S3. Historical data collection: Export the data of relevant parameters from the SIS system. It is best to export the parameter data for a historical year, so that the operating conditions of the four seasons can be analyzed in detail.

[0042] S4. Data cleaning: Empty and remove data of the same dimension in a year, and clean up data of abnormal load stages to obtain historical data of stable working conditions.

[0043] S5. Big data algorithm: linear regression.

[0044] For the main pipe heating unit, its steam consumption characteristic curve is the basis for the optimal distribution of thermal power load. Although this method requires a large amount of real-time (historical) operation data of the on-site units and the fitting workload is relatively large, this model has high accuracy, can more accurately reflect the system characteristics, and is conducive to guiding the next stage of real-time load distribution. For the optimal value of the steam consumption characteristic coefficient of the corresponding steam turbine type, the formula for the residual sum of squares based on the data value of the steam consumption characteristic curve is written as, , in, Expressed as the residual sum of squares, is the total number of samples, Expressed as actual value, Dependent variables expressed as predicted values, such as the slight increase rate of steam consumption for power generation, the slight increase rate of steam consumption for production extraction, and the slight increase rate of steam consumption for heating extraction. Expressed as a proxy for the unknown quantity.

[0045] The partial derivative for each unknown quantity is expressed as,

[0046] Minimize the residual sum of squares and set the partial derivatives equal to 0. The resulting rectangular matrix is ​​as follows. Solving it will yield the values ​​of each unknown quantity: .

[0047] The closeness function is used to measure the closeness of the regression linear equation obtained by the least squares method with the observed data. It is expressed as, , , in, Expressed as the number of variables, Represented as actual value.

[0048] when The closer it is to or equal to 1, the higher the reference value of the related equation, that is, the reliability of the fitted function curve is high, and it can be considered to meet the function requirements of linear programming; on the contrary, the closer it is to 0, the lower the reference value, that is, the reliability of the fitted function curve is low, and it does not meet the function requirements of linear programming. Generally speaking, when When , it means that the relevant equation has a high reference value, that is, the fitted function curve has high reliability and meets the function requirements of linear programming; on the contrary, when When , it indicates that the reference value is low, that is, the reliability of the fitted function curve is low and does not meet the function requirements of linear programming. Of course, data analysis software such as MATLAB can also be used to directly obtain the value of the characteristic coefficient.

[0049] S6. Mathematical optimization algorithm: linear programming.

[0050] Mathematical modeling is carried out using the linear programming method in operations research. This method is mainly used to study the minimum or maximum value of linear functions. The mathematical model of the linear programming method satisfies three elements: ① linear constraints related to independent variables; ② the values ​​of independent variables are subject to certain restrictions; ③ the objective function satisfies linear conditions. From these three elements, it can be seen that the linear programming method is suitable for solving the type of problems. For the load optimization distribution problem of the mother tube unit, the characteristic equation on the boiler side is generally a polynomial, while the characteristic equation on the turbine side satisfies a linear relationship, so the linear programming method can be applied to the optimization problem on the turbine side.

[0051] Different linear programming problems have different mathematical model expressions, but the general linear programming problem can be transformed into the following form to describe it. The general form of the linear programming problem is as follows: Objective function: , Constraints: , in, Represented as decision variables, there are indivual; , , Expressed as a constant, =1,2,3,,, ; =1,2,3,,, .

[0052] Solving a linear programming problem is to solve a set of data under all constraints so that the objective function achieves the maximum (minimum) value.

[0053] S7. Front-end display: The final calculated results are displayed on the platform, and real-time push and quantitative data optimization suggestions are given to on-site operators.

[0054] Example 2

[0055] Reference Figure 2 , which is the second embodiment of the present invention, and is different from the first embodiment in that: the method for distributing thermal power loads of a main control unit based on a big data algorithm also includes, in order to verify and illustrate the technical effects adopted in this method, this embodiment adopts a traditional technical solution and the method of the present invention for comparative testing, and compares the test results by means of scientific demonstration to verify the real effect of this method.

[0056] The essence of turbine side load optimization is to distribute the loads of the two units under the premise of meeting the total gas consumption for production and life, so as to minimize the total new steam volume. Taking the two units of the thermal power plant as an example, the #5 and #6 units are set as the model. The mathematical model is established based on the solved steam consumption characteristic equation, and the optimization is carried out according to the linear programming method described above. According to the historical data of the operation of the #5 and #6 units of the thermal power plant, the five sets of data given in Table 1 are optimized and analyzed, and then the optimization results are analyzed to determine the optimization method for the final project implementation.

[0057] Table 1: Actual operation data of two sets of units

[0058] The linear programming method proposed in this invention is used to model the following: Objective function: L L , Constraints: , in, Expressed as the power generation required for production and living, The model is solved to obtain the optimal allocation result; then the genetic algorithm and particle swarm algorithm are used to solve the optimization respectively, and finally the optimization result of the present invention is compared with the optimization results of the genetic algorithm and the particle swarm algorithm. The specific experimental data of the comparison are as follows: Figure 2 The running result data are shown in Tables 2, 3 and 4.

[0059] Table 2: Linear programming optimization results data table

[0060] Table 3: Genetic algorithm optimization results data table

[0061] Table 4: Particle swarm optimization results data table

[0062] It can be seen from the changes in the total fresh steam volume before and after optimization that the three methods have certain optimization effects; compared with the optimization results of the three methods, the optimization effect of the linear programming method is significantly better than that of the genetic algorithm and the particle swarm algorithm. Through the comparison of the results of this example, the linear programming method is selected as the optimization algorithm for the turbine side in the two-level load optimization scheme.

[0063] Example 3

[0064] The third embodiment of the present invention is different from the first two embodiments in that: a system of a method for distributing thermal power loads of a main control unit based on a big data algorithm comprises a real-time data acquisition module, a real-time data storage module and a SIS functional module.

[0065] As a monitoring information system, the SIS system provides services for the automation and informatization of the entire power plant production. It is essentially a system platform for receiving, processing and publishing the original production data from the DCS control system and other auxiliary control systems. Therefore, from the perspective of data flow, the system mainly consists of data acquisition, data storage, data processing and processing, and data publishing. Its corresponding system hardware architecture can be divided into: front-end real-time data acquisition system (acquisition), real-time / historical data server (storage), SIS functional station (data mining, calculation and analysis of the background engine of the BS architecture), and front-end display (front-end of the BS architecture).

[0066] The real-time data acquisition module of the present invention collects real-time production data from DCS, ECS, chemical water PLC, and SCADA production control systems through a gateway machine. By building a plant-level process data platform, the process data that were originally from scattered, independent, and unrelated sources are integrated into a unified database in chronological order, providing the entire plant with a data platform that is unified in access, automatic, continuous, highly real-time, and has massive storage.

[0067] The real-time data storage module is the unified data platform for the whole plant, the core of the entire SIS, and the platform for carrying real-time / historical databases. Since the production process data of power plants is large in volume, has high precision requirements, and has time tags, it is not suitable to use conventional relational database storage, but a real-time / historical database with real-time data processing functions should be used. For thermal power load optimization products under the BS architecture, a large amount of historical data is required for in-depth mining and calculation and analysis. Therefore, this is a solid foundation.

[0068] The SIS functional module backend is equipped with the highest performance software computing engine currently available, which can read a large amount of historical data from the real-time data storage module, conduct big data analysis, such as listing, data cleaning and emptying, deeply explore its characteristics, and calculate extreme values ​​in real time. Finally, the platform is displayed to push real-time and quantitative data optimization suggestions to on-site operators.

[0069] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0071] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0072] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for distributing thermal power load of a main control unit based on a big data algorithm, characterized in that: include, Determine the turbine type and select the mathematical model based on the turbine type; After obtaining relevant parameters according to the steam turbine type analysis mechanism, the data of relevant parameters are exported from the SIS system. The exported data is historical data for one year. Clean the exported data to obtain historical data of stable working conditions; Based on the historical data of stable working conditions, the steam consumption characteristic curve of each steam turbine of the main tube heating unit is fitted; The steam consumption characteristic curve is analyzed, and the linear programming method is used to build a mathematical model, and the model is solved to obtain the optimal allocation plan.

2. The method for distributing thermal power load of a main control unit based on a big data algorithm according to claim 1, characterized in that: The steam turbine types include pure condensing, back pressure, extraction condensing and double extraction units.

3. The method for distributing thermal power load of a main control unit based on a big data algorithm according to claim 1 or 2, characterized in that: The mathematical model is selected according to the type of steam turbine, including: the mathematical model of the pure condensing type is expressed as: ， in, Expressed as the unit's new steam volume, Expressed as the electrical power of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the pure condensing unit. It is expressed as the no-load steam consumption of the main steam related to the pure condensing unit; The mathematical model of the back pressure type is expressed as: ， ， in, Expressed as the extraction steam heat load of the unit, It is expressed as the slight increase rate of power generation steam consumption of the back pressure unit related main steam, It is expressed as the no-load steam consumption of the main steam related to the back pressure unit; It is expressed as the slight increase rate of steam consumption for power generation related to the extraction of steam from the back pressure unit. Expressed as the no-load steam consumption of the extraction steam related to the back pressure unit.

4. The method for distributing thermal power load of a main control unit based on a big data algorithm according to claim 3, characterized in that: The mathematical model is selected according to the type of steam turbine, and further includes that the mathematical model of the extraction-condensation type is expressed as: ， in, Expressed as the total steam consumption of the unit, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the single extraction unit. It is expressed as the slight increase rate of extraction steam consumption of main steam related to single extraction unit; It is expressed as the no-load steam consumption of the main steam related to the single extraction unit; The mathematical model of the double extraction unit is expressed as: ， in, Expressed as the total heat consumption of the unit, It represents the electrical load borne by the unit. Expressed as the heat load of the high-pressure steam extraction port, Expressed as the heat load of the low-pressure steam extraction port, It is expressed as the slight increase rate of power generation steam consumption of the main steam of the double extraction unit. It is expressed as the slight increase rate of production extraction steam consumption of main steam related to double extraction units; It is expressed as the slight increase rate of heating extraction steam consumption of the main steam of the double extraction unit. It is expressed as the no-load steam consumption of the main steam related to the double-extraction unit.

5. The method for distributing thermal power load of a main control unit based on a big data algorithm according to claim 1, characterized in that: The analysis of the steam consumption characteristic curve includes, for the best value of the steam consumption characteristic coefficient of the corresponding steam turbine type, writing the residual square sum formula based on the data value of the steam consumption characteristic curve as follows: ， in, Expressed as the residual sum of squares, is the total number of samples, Expressed as actual value, Denote the dependent variable as the predicted value, It is expressed as a substitute for the unknown quantity; The partial derivative for each unknown quantity is expressed as, ， Minimize the residual sum of squares and set the partial derivatives equal to 0. The resulting rectangular matrix is ​​as follows. Solving it will yield the values ​​of each unknown quantity: 。 6. The method for distributing thermal power loads of bus-pipe units based on big data algorithm according to claim 5, characterized in that: The analysis of the steam consumption characteristic curve also includes using a close function to measure the closeness of the regression linear equation obtained by the least squares method and the observed data. The close function It is expressed as, ， ， in, Expressed as the number of variables, Expressed as actual value; when When , it means that the relevant equation has a high reference value, that is, the fitted function curve has high reliability and meets the function requirements of linear programming; on the contrary, when When , it indicates that the reference value is low, that is, the reliability of the fitted function curve is low and does not meet the function requirements of linear programming.

7. A thermal power load distribution system for busbar control units based on big data algorithm, characterized by: include, Real-time data collection module, used to collect real-time production data; Real-time data storage module, used for data storage; as well as, SIS functional module is used to retrieve data from the real-time data storage module for real-time analysis.

8. The main control unit thermal power load distribution system based on big data algorithm according to claim 7, characterized in that: The real-time data acquisition module collects real-time production data from DCS, ECS, chemical water PLC, and SCADA production control systems through the gateway machine, and integrates the process data originally from scattered and independent sources and unrelated to each other into a unified database in chronological order by building a plant-level process data platform; The SIS functional module reads a large amount of historical data from the real-time data storage module, performs big data analysis including data cleaning and emptying, deeply mines data characteristics, and calculates extreme values ​​in real time, and finally displays the data on the platform, pushes real-time data, and provides quantitative data optimization suggestions to on-site operators.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for distributing thermal and electric loads of bus control units based on big data algorithm are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for distributing thermal and electric loads of the main control unit based on the big data algorithm are implemented.

Images