A method for real-time prediction of external heat load of thermal power plants

Abstract

This invention relates to the field of heating load monitoring technology for thermal power plants, and particularly to a method for real-time prediction of external heating load in thermal power plants. The method includes the following steps: acquiring historical heating data from the operating system of a single heating unit in the heating area, and removing data with a heating load less than zero; selecting steam extraction data for each period of the past two years from the heating units, and analyzing data from three typical working days each month (early, middle, and late ten days); dividing the year into four seasons to reflect different changes in heating demand, and selecting typical working days for data analysis; obtaining the relationship between steam extraction volume and time through formula fitting, and dynamically correcting using real-time monitored steam extraction volume to predict the steam extraction volume at a future point in time. This method can achieve efficient and accurate dynamic prediction of heating load, providing data support for the economic operation of combined heat and power units, improving heating reliability, and reducing risks caused by load fluctuations.

Description

Technical Field

[0001] This invention relates to the field of heat load monitoring technology for thermal power plants, and particularly to a method for real-time prediction of the external heat load of thermal power plants. Background Technology

[0002] Heat load forecasting is a key aspect of thermal power plant operation. With the continuous growth of energy demand and the increasing volatility of power grid load, the role of combined heat and power (CHP) units in the power system is becoming increasingly important. CHP systems can not only efficiently utilize waste heat for heating or industrial heat use, thereby improving energy efficiency, but also provide electricity.

[0003] Ensuring stable heating supply while maintaining reliable and flexible power supply has become a critical issue during peak electricity consumption periods. Therefore, heat load forecasting is particularly important. Accurate heat load forecasting provides reliable data support for the operation of heating units. By accurately predicting heat load, unit operation can be optimized, giving them greater flexibility and adjustment capabilities during peak electricity consumption periods. This not only helps improve the reliability of the power supply system but also effectively ensures the stability of heating supply and reduces the risks caused by load fluctuations.

[0004] Current heat load forecasting methods suffer from high computational complexity and sensitivity in large-scale data processing and parameter tuning. They also have high parameter and model complexity, are highly dependent on data, and their accuracy is affected when data is insufficient or highly variable. Furthermore, the complex data processing process can impact the efficiency and reliability of practical applications. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and propose a real-time prediction method for the external heat supply load of thermal power plants. This method can accurately predict the heat load, provide reliable data support for the economic operation of combined heat and power units, enable them to have greater flexibility and adjustment capabilities during peak electricity consumption periods, improve the reliability of the heating system, and reduce the risks caused by load fluctuations.

[0006] To achieve the above objectives, the present invention adopts the following specific technical solution:

[0007] This invention provides a method for real-time prediction of external heat supply load of a thermal power plant, comprising the following steps:

[0008] S1. Obtain and filter historical heating data; obtain historical heating data from the operation system of a single heating unit of a power plant in the heating area, perform time-series processing, average the heating amount by hour, and remove data with a heating amount less than zero.

[0009] S2. Based on geographical location characteristics, the climate throughout the year is divided into seasons; based on the months contained in each season, the month is used as the first variable to establish the correlation between the month and the amount of steam extracted for heating.

[0010] S3. Select typical data for analysis; select the steam extraction volume data of each section of the heating unit in the past two years, and select 3 typical working days in the first ten days, middle ten days and last ten days of each month for data analysis, and establish a heating steam extraction volume prediction model with "day" as the second variable to realize the correlation between "day" and heating steam extraction volume.

[0011] S4. Fitting the daily heating load formula: Fit the average heating steam extraction data of the selected typical working days to obtain the relationship between the heating steam extraction volume and time in each segment of the heating steam extraction volume prediction model, so as to predict the trend of the heating steam extraction volume in each segment at a certain time in the future.

[0012] S5. Monitor the current steam extraction data for heating in real time and correct the formula to improve the accuracy of prediction.

[0013] Furthermore, in step S4, the daily heating load formula fitting is as follows:

[0014] F cr,i (x)=a i,4 x 4 +a i,3 x 3 +a i,2 x 2 +a i,1 x+A i ;

[0015] F r,i (x)=b i,4 x 4 +b i,3 x 3 +b i,2 x 2 +b i,1 x+B i ;

[0016] F lr,i (x)=c i,4 x 4 +c i,3 x 3 +c i,2 x 2 +c i,1 x+C i ;

[0017] F zr,i (x)=d i,4 x 4 +d i,3 x 3 +di,2 x 2 +d i,1 x+D i ;

[0018] G cro =F cr,i (x);

[0019] G ro =F r,i (x);

[0020] G lro =F lr,i (x);

[0021] G zro =F zr,i (x);

[0022] Where x represents the current time, such as a certain time, h; a i,4 a is the fourth-order coefficient of the heating formula for a certain season; i,3 a is the third-order coefficient of the heating formula for a certain season; i,2 a represents the second-order coefficient of the heating formula for a certain season; i,1 A represents the first-order coefficient of the heating formula for a certain season; i This is a constant in the heating formula for a certain season;

[0023] b i,4 b represents the fourth-order coefficient of the seasonal heat reheat formula; i,3 b represents the third-order coefficient of the heat reheat formula for a certain season; i,2 b represents the second-order coefficient of the seasonal heat reheat formula; i,1 B represents the first-order coefficient of the heat reheat formula for a certain season; i This is a constant in the heat reheat formula for a certain season;

[0024] c i,4 c represents the fourth-order coefficient of the cold reheat formula for a certain season; i,3 c represents the third-order coefficient of the cold reheat formula for a certain season; i,2 c represents the second-order coefficient of the cold reheat formula for a certain season; i,1 C represents the first-order coefficient of the cold reheat formula for a certain season; i This is a constant in the cold reheat formula for a certain season;

[0025] d i,4 d represents the fourth-order coefficient of the heating formula for a certain season; i,3 d represents the third-order coefficient of the heating formula for a certain season; i,2 d represents the second-order coefficient of the heating formula for a certain season; i,1 D represents the first-order coefficient of the heating formula for a certain season; iThis is a constant in the heating formula for a certain season;

[0026] i represents the season: Spring (1): March-June; Summer (2): July-September; Autumn (3): October-November; Winter (4): December-February of the following year; G cr0 , G r0 , G lr0 , G zr0 These are the predicted average heat supply from the first extraction, the hot reheat, the cold reheat, and the intermediate discharge, in t / h.

[0027] Furthermore, in step S5, the current steam extraction data for heating is monitored in real time and the formula is corrected. The corrected formula is as follows:

[0028]

[0029] Where Δx is the time difference between a future time and the current time, h; G cr1 , G r1 , G lr1 , G zr1 These are the predicted dynamic heat supply from primary extraction, hot reheat, cold reheat, and intermediate discharge, respectively, in t / h.

[0030] The present invention can achieve the following technical effects:

[0031] The real-time forecasting method for external heat load of thermal power plants provided by this invention significantly improves the accuracy of heat load forecasting through seasonal division, data selection and analysis, formula fitting, and real-time monitoring and model correction. This provides reliable data support for the scheduling and operation of combined heat and power (CHP) units, ensuring the efficient and stable operation of the power system. During implementation, the data selection and model correction methods can be continuously optimized based on actual conditions to further improve forecast accuracy and model adaptability, ensuring high forecast accuracy under different operating conditions. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating a method for real-time prediction of external heat load from a thermal power plant, provided by an embodiment of the present invention.

[0033] Figure 2 This is a comparison curve of the predicted cold reheating data and the actual heating supply obtained by the real-time prediction method of heating load in winter for a 300MW unit according to an embodiment of the present invention.

[0034] Figure 3 This is a comparison curve of the predicted heat resupply data and the actual heat supply obtained by the real-time prediction method of heating load in spring for a 300MW unit according to an embodiment of the present invention. Detailed Implementation

[0035] In the following description, embodiments of the invention will be described with reference to the accompanying drawings. In the description below, the same modules are denoted by the same reference numerals. Where the same reference numerals are used, their names and functions are also the same. Therefore, their detailed description will not be repeated.

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not constitute a limitation thereof.

[0037] This invention provides a method for real-time prediction of the external heat supply load of a thermal power plant, the process of which is as follows: Figure 1 As shown, firstly, historical heating data is obtained from the operating system of a single heating unit in the power plant within the heating area. Using a positive value for the extracted steam volume as a criterion, data with a heating volume less than zero is considered invalid and discarded. Secondly, heating steam volume data for each period of the past two years is selected, with three typical working days chosen each month (early, middle, and late ten days) for data analysis. Thirdly, the year is simply divided into four quarters to reflect changes in heating demand during different seasons, and typical working days are selected from the historical database for data analysis. Finally, a formula is fitted to derive the relationship between heating steam volume and time, and based on this, the obtained relationship is dynamically corrected using real-time monitored heating steam volume. This allows for accurate prediction of heating steam volume at a future point in time. This invention enables efficient, fast, and accurate dynamic prediction of heating load, providing reliable data support for the economic operation of combined heat and power (CHP) units, thereby improving the reliability of the heating system and reducing the risks caused by load fluctuations.

[0038] Specifically, the present invention provides a method for real-time prediction of the external heat supply load of a thermal power plant, comprising the following steps:

[0039] S1. Obtain and filter historical heating data.

[0040] Historical heating data is obtained from the operation systems of individual heating units in power plants within the heating area. This data is then processed using time-series methods, averaging the heating output over hourly intervals. Invalid data is removed, with positive steam extraction rates used as the criterion; data with a heating output less than zero is considered invalid and discarded. This processing method effectively avoids data distortion and improves forecast accuracy.

[0041] S2. Based on geographical location characteristics, the climate throughout the year is divided into seasons.

[0042] Based on the months included in each season, the month is used as the primary variable to correlate the month with the amount of steam extracted for heating. Based on the annual climate change patterns and heating demand characteristics, the year is divided into four seasons: spring (March-June), summer (July-September), autumn (October-November), and winter (December-February of the following year). This seasonal division method is simple and easy to implement, and can effectively reflect the impact of different seasons on heating load. For example, heating demand is typically higher in winter and spring, while it is relatively lower in summer due to higher temperatures. This seasonal division allows for a better capture of the seasonal variation patterns of heating load, laying the foundation for subsequent data analysis and model building.

[0043] S3. Select typical data for analysis.

[0044] Data on steam extraction from various sections of the heating unit over the past two years were selected, and three typical working days were chosen each month for analysis, divided into the first, middle, and last ten days. These typical working days should be representative and reflect the monthly heating load changes. This data includes key indicators such as the unit's primary extraction heat supply, hot reheat heat supply, cold reheat heat supply, and intermediate exhaust heat supply. In-depth analysis of this data reveals the temporal variation patterns of the heating load, establishing a steam extraction prediction model with "day" as the second variable. This model establishes a correlation between "day" and steam extraction volume, providing fundamental data support for the prediction model.

[0045] S4, daily heating load formula fitting.

[0046] By fitting the average steam extraction data of selected typical working days, the relationship between the steam extraction volume of each segment and time in the steam extraction volume prediction model is obtained, so as to predict the trend of the steam extraction volume of each segment at a certain time in the future.

[0047] Based on data analysis, a predictive model is established by fitting a formula to the daily heating load. The goal of the formula fitting is to establish a mathematical relationship between the average steam extraction volume for heating on a typical workday and time, thereby accurately predicting changes in the steam extraction volume for heating at various future times. The relationships between the steam extraction volume and time for each segment in the predictive model are as follows:

[0048] F cr,i (x)=a i,4 x 4 +a i,3 x 3 +a i,2 x 2 +a i,1 x+A i (1)

[0049] F r,i (x)=b i,4 x4 +b i,3 x 3 +b i,2 x 2 +b i,1 x+B i (2)

[0050] F lr,i (x)=c i,4 x 4 +c i,3 x 3 +c i,2 x 2 +c i,1 x+C i (3)

[0051] F zr,i (x)=d i,4 x 4 +d i,3 x 3 +d i,2 x 2 +d i,1 x+D i (4)

[0052] G cro =F cr,i (x); (5)

[0053] G ro =F r,i (x); (6)

[0054] G lro =F lr,i (x); (7)

[0055] G zro =F zr,i (x); (8)

[0056] Where x is the current time, such as h at a certain time; a i,4 a is the fourth-order coefficient of the heating formula for a certain season; i,3 a is the third-order coefficient of the heating formula for a certain season; i,2 a represents the second-order coefficient of the heating formula for a certain season; i,1 A represents the first-order coefficient of the heating formula for a certain season; i This is a constant in the heating formula for a certain season;

[0057] b i,4 b represents the fourth-order coefficient of the seasonal heat reheat formula; i,3 b represents the third-order coefficient of the heat reheat formula for a certain season; i,2 b represents the second-order coefficient of the seasonal heat reheat formula;i,1 B represents the first-order coefficient of the heat reheat formula for a certain season; i This is a constant in the heat reheat formula for a certain season;

[0058] c i,4 c represents the fourth-order coefficient of the cold reheat formula for a certain season; i,3 c represents the third-order coefficient of the cold reheat formula for a certain season; i,2 c represents the second-order coefficient of the cold reheat formula for a certain season; i,1 C represents the first-order coefficient of the cold reheat formula for a certain season; i This is a constant in the cold reheat formula for a certain season;

[0059] d i,4 d represents the fourth-order coefficient of the heating formula for a certain season; i,3 d represents the third-order coefficient of the heating formula for a certain season; i,2 d represents the second-order coefficient of the heating formula for a certain season; i,1 D represents the first-order coefficient of the heating formula for a certain season; i This is a constant in the heating formula for a certain season;

[0060] i represents the season: Spring (1): March-June; Summer (2): July-September; Autumn (3): October-November; Winter (4): December-February of the following year; G cr0 , G r0 , G lr0 , G zr0 These are the predicted average heat supply from the first extraction, the hot reheat, the cold reheat, and the intermediate discharge, in t / h.

[0061] S5. Monitor the current steam extraction data for heating in real time and correct the formula to improve the accuracy of prediction.

[0062] To improve the accuracy of predictions, this invention introduces a real-time monitoring and model correction mechanism. This mechanism monitors the current steam extraction data for heating in real time and uses this data to dynamically correct the obtained formula. The corrected formula is as follows:

[0063]

[0064] Where Δx is the time difference between a future time and the current time, h; G cr1 , G r1 , G lr1 , G zr1 These are the predicted dynamic heat supply from primary extraction, hot reheat, cold reheat, and intermediate discharge, respectively, in t / h.

[0065] The following describes a method for real-time prediction of external heat load from thermal power plants, using specific examples.

[0066] Example 1

[0067] Step 1: Historical data acquisition and filtering;

[0068] Historical heating data is obtained from the operation system of individual heating units in the power plant within the heating area. The data is then processed for time series analysis, with the heating output averaged over hourly intervals. Invalid data is deleted, and data with a heating output less than zero is considered invalid and discarded, using a positive steam extraction rate as the criterion.

[0069] Step 2: Seasonal Division;

[0070] Based on regional geographical characteristics, the annual climate is divided into four seasons: spring (March-June), summer (July-September), autumn (October-November), and winter (December-February of the following year). The months within each season are used as the primary variable to correlate the month with the amount of steam extracted for heating. This seasonal division method effectively reflects the impact of different seasons on heating load and better captures the seasonal variation patterns of heating load.

[0071] Step 3: Selection and analysis of typical data;

[0072] We selected steam extraction data from various sections of the heating unit over the past two years. Each month, we analyzed three typical working days (early, middle, and late ten days) to establish a steam extraction prediction model with the "day" as the second variable, thus establishing a correlation between the "day" and the steam extraction volume. The selected typical working days should be representative and reflect the monthly heating load changes. This data includes key indicators of steam extraction volume from each section of the unit. In-depth analysis of this data reveals the patterns of heating load variation over time, providing fundamental data support for establishing the prediction model.

[0073] Step 4: Fitting the daily heating load formula;

[0074] Multivariate nonlinear fitting was performed on the average steam extraction volume data of selected typical working days to obtain the relationship between the steam extraction volume and time for each segment in the prediction model. The obtained relationship can well reflect the temporal variation law of the steam extraction volume, so as to predict the trend of the steam extraction volume for each segment at a certain time in the future.

[0075] Step 5: Real-time monitoring and model correction;

[0076] By monitoring the current steam extraction data for heating in real time and using this data to revise the model of the obtained relationship, the accuracy of the prediction can be improved, ensuring that the prediction results are highly consistent with the actual situation.

[0077] Figure 2 and Figure 3The figure shows a comparison curve between the predicted heating load data for winter cold reheat and spring hot reheat obtained by a real-time heating load prediction method for a certain thermal power unit and the actual heating load.

[0078] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0079] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0080] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for real-time prediction of external heat supply load of a thermal power plant, characterized in that, Includes the following steps: S1. Obtain and filter historical heating data; obtain historical heating data from the operation system of a single heating unit of a power plant in the heating area, perform time-series processing, average the heating amount by hour, and remove data with a heating amount less than zero. S2. Based on geographical location characteristics, the climate throughout the year is divided into seasons; based on the months contained in each season, the month is used as the first variable to establish the correlation between the month and the amount of steam extracted for heating. S3. Select typical data for analysis; select the steam extraction volume data of each section of the heating unit in the past two years, and select 3 typical working days in the first ten days, middle ten days and last ten days of each month for data analysis, establish a heating steam extraction volume prediction model with "day" as the second variable, and realize the correlation between "day" and heating steam extraction volume. S4. Fitting the daily heating load formula: Fit the average heating steam extraction data of the selected typical working days to obtain the relationship between the heating steam extraction volume and time in each segment of the heating steam extraction volume prediction model, so as to predict the trend of the heating steam extraction volume in each segment at a certain time in the future. The specific fitting of the daily heating load formula is as follows: F cr,i (x)=a i,4 x 4 +a i,3 x 3 +a i,2 x 2 +a i,1 x+A i ; F r,i (x)=b i,4 x 4 +b i,3 x 3 +b i,2 x 2 +b i,1 x+B i ; F lr,i (x)=c i,4 x 4 +c i,3 x 3 +c i,2 x 2 +c i,1 x+C i ; F zr,i (x)=d i,4 x 4 +d i,3 x 3 +d i,2 x 2 +d i,1 x+D i ; G cro =F cr,i (x); G ro =F r,i (x); G lro =F lr,i (x); G zro =F zr,i (x); Where x is the current time; a i,4 a is the fourth-order coefficient of the heating formula for a certain season; i,3 a is the third-order coefficient of the heating formula for a certain season; i,2 a represents the second-order coefficient of the heating formula for a certain season; i,1 A represents the first-order coefficient of the heating formula for a certain season; i This is a constant in the heating formula for a certain season; b i,4 b represents the fourth-order coefficient of the seasonal heat reheat formula; i,3 b represents the third-order coefficient of the heat reheat formula for a certain season; i,2 b represents the second-order coefficient of the seasonal heat reheat formula; i,1 B represents the first-order coefficient of the heat reheat formula for a certain season; i This is a constant in the heat reheat formula for a certain season; c i,4 c represents the fourth-order coefficient of the cold reheat formula for a certain season; i,3 c represents the third-order coefficient of the cold reheat formula for a certain season; i,2 c represents the second-order coefficient of the cold reheat formula for a certain season; i,1 C represents the first-order coefficient of the cold reheat formula for a certain season; i This is a constant in the cold reheat formula for a certain season; d i,4 d represents the fourth-order coefficient of the heating formula for a certain season; i,3 d represents the third-order coefficient of the heating formula for a certain season; i,2 d represents the second-order coefficient of the heating formula for a certain season; i,1 D represents the first-order coefficient of the heating formula for a certain season; i This is a constant in the heating formula for a certain season; i represents the season: Spring (1): March-June; Summer (2): July-September; Autumn (3): October-November; Winter (4): December-February of the following year; G cr0 , G r0 , G lr0 , G zr0 These are the predicted average heat supply from the first extraction, the heat supply from the hot re-extraction, the heat supply from the cold re-extraction, and the heat supply from the intermediate discharge, respectively, in t / h. S5. Monitor the current steam extraction data for heating in real time and correct the formula to improve the accuracy of the prediction; The current steam extraction rate for heating is monitored in real time, and the formula is corrected accordingly. The corrected formula is as follows: Where Δx is the time difference between a future time and the current time, h; G cr1 , G r1 , G lr1 , G zr1 These are the predicted dynamic heat supply from primary extraction, hot reheat, cold reheat, and intermediate discharge, respectively, in t / h.

Images