A provincial coal-fired power generation carbon emission monitoring and management method and system

Abstract

The present invention discloses a provincial coal-fired power generation carbon emission monitoring and management method and system, belonging to the field of carbon emission monitoring and management technology. The method includes establishing an electricity price calculation function using a preset electricity price coefficient and a preset electricity price base; establishing a carbon emission prediction model, and using the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value; selecting an electricity price coefficient based on the size of the carbon emission prediction value, the electricity price coefficient including a first coefficient, a second coefficient, and a third coefficient; and calculating the current electricity price using the electricity price calculation function based on the selected electricity price coefficient, and issuing an early warning message. The present invention can achieve accurate monitoring and effective management of carbon emissions from provincial coal-fired power generation through a management mechanism that links electricity prices with carbon emissions.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring and management, and in particular to a provincial coal-fired power generation carbon emission monitoring and management method and system. Background Art

[0002] With the increasing severity of global climate change, carbon emissions management has become a key concern. As a major source of carbon emissions, coal-fired power generation makes monitoring and managing its carbon emissions crucial for achieving emission reduction targets. However, existing methods for monitoring and managing carbon emissions from coal-fired power generation have numerous shortcomings.

[0003] At present, the carbon emission monitoring methods at home and abroad mainly include inventory compilation method, actual measurement method, material balance method, model method, etc. When these methods are applied to provincial coal-fired power generation carbon emission monitoring, they often have problems such as single measurement object and incomplete measurement data, which makes it difficult to meet the needs of accurate monitoring and management; at the same time, electricity price, as an important means to regulate the supply and demand relationship in the electricity market, has a close relationship with carbon emissions. However, the existing electricity price mechanism often fails to fully consider carbon emission factors, resulting in its limited role in promoting energy conservation and emission reduction; in view of the limitations of existing carbon emission monitoring methods and the complexity of the relationship between electricity price and carbon emissions, an innovative provincial coal-fired power generation carbon emission monitoring and management method is needed to achieve accurate monitoring and effective management of coal-fired power generation carbon emissions. Summary of the Invention

[0004] To solve the above problems, the present invention provides a provincial coal-fired power generation carbon emission monitoring and management method and system, which adopts a management mechanism that links electricity prices with carbon emissions, and can achieve accurate monitoring and effective management of provincial coal-fired power generation carbon emissions.

[0005] The above objectives can be achieved through the following solutions:

[0006] A provincial coal-fired power generation carbon emission monitoring and management method includes: using a preset electricity price coefficient and a preset electricity price base to establish an electricity price calculation function. For the electricity price p,

[0007] p=μ*D,

[0008] In the formula, μ is the electricity price coefficient, and D is the electricity price base; a carbon emission prediction model is established, and the carbon emission prediction model is used to predict carbon emissions to obtain a carbon emission prediction value; the electricity price coefficient is selected according to the size of the carbon emission prediction value, and the electricity price coefficient includes a first coefficient, a second coefficient, and a third coefficient; based on the selected electricity price coefficient, the current electricity price is calculated using the electricity price calculation function, and an early warning message is issued.

[0009] Optionally, the use of a preset electricity price coefficient and a preset electricity price base to establish an electricity price calculation function includes: collecting historical operating data of a coal-fired power plant, local historical economic indicators, historical electricity demand data and historical electricity prices to obtain a first training set; using the historical operating data of the coal-fired power plant, local historical economic indicators and historical electricity demand data as input, and historical electricity prices as output, using the first training set to establish and train a neural network model to obtain an electricity price base prediction model; collecting current operating data of the coal-fired power plant, local current economic indicators, and current electricity demand data to obtain an electricity price basic data set; and inputting the electricity price basic data set into the electricity price base prediction model to obtain the current electricity price base.

[0010] Optionally, establishing a carbon emission prediction model includes: collecting historical carbon emission data, historical meteorological data, and historical power generation data of coal-fired power plants to construct a comprehensive factor data set; preprocessing the comprehensive factor data set to obtain a second training set; and using the second training set to establish and train a neural network model to obtain a carbon emission prediction model.

[0011] Optionally, the use of the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value includes: collecting current carbon emission data, current meteorological data, and current power generation data of the coal-fired power plant to obtain a real-time data set; inputting the real-time data set into the carbon emission prediction model to obtain a carbon emission prediction value.

[0012] Optionally, the method also includes: collecting actual carbon emission values ​​of coal-fired power plants; calculating the error between the actual carbon emission values ​​and the predicted carbon emission values; when the error is greater than a preset error threshold, using a back propagation algorithm to iteratively optimize the parameters in the carbon emission prediction model; when the error is less than or equal to the error threshold or the number of iterations reaches an upper limit, stopping the optimization to obtain the final carbon emission prediction model.

[0013] Optionally, selecting the electricity price coefficient based on the size of the carbon emission prediction value includes: judging whether the carbon emission prediction value is greater than a preset first threshold; if the carbon emission prediction value is greater than the first threshold, selecting the first coefficient; if the carbon emission prediction value is less than or equal to the first threshold, judging whether the carbon emission prediction value is greater than a second threshold; if the carbon emission prediction value is greater than the second threshold, selecting the second coefficient; if the carbon emission prediction value is less than or equal to the second threshold, selecting the third coefficient.

[0014] Optionally, the method further includes: collecting historical carbon emission data of each coal-fired power plant and calculating a carbon emission median; obtaining a carbon emission target value from a preset database; and calculating the first threshold value using the carbon emission target value and the carbon emission median. For the first threshold value x1,

[0015] x1=c1(m*z+n*G)+k1,

[0016] Where c1 is the coefficient of variation of the first threshold, m is the weight coefficient of the median carbon emissions, Z is the median carbon emissions, n is the weight coefficient of the carbon emission target value, G is the carbon emission target value, and k1 is the error coefficient of the second threshold. The second threshold is calculated using the carbon emission target value and the median carbon emissions. For the second threshold x2,

[0017] x2=c2*(m*Z+n*G)-k2,

[0018] Wherein, c2 is the variation coefficient of the second threshold, and k2 is the error coefficient of the second threshold.

[0019] Optionally, the method further includes: collecting carbon emission data and operating data of the coal-fired power plant, and calculating the carbon emission change rate and the operating change rate; using the carbon emission change rate and the operating change rate to calculate a risk assessment value, for the risk assessment value f, there is

[0020] f=α*T+β*Q+λ,

[0021] In the formula, α is the weight coefficient of the carbon emission change rate, T is the carbon emission change rate, β is the weight coefficient of the operating change rate, Q is the operating data, and λ is the error coefficient.

[0022] Optionally, the method also includes: when the risk assessment value is greater than a preset third threshold, determining whether the risk assessment value is greater than a preset fourth threshold; if not, adjusting the variation coefficient of the first threshold, the error coefficient of the first threshold, the variation coefficient of the second threshold, and the error coefficient of the second threshold; if so, adjusting the carbon emission target value.

[0023] Based on the same inventive concept, the present invention also provides a provincial coal-fired power generation carbon emission monitoring and management system, the system including: a carbon emission prediction module, used to establish a carbon emission prediction model, and use the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value; an electricity price coefficient selection module, used to select the electricity price coefficient according to the size of the carbon emission prediction value, the electricity price coefficient includes a first coefficient, a second coefficient and a third coefficient; an electricity price calculation module, used to use a preset electricity price coefficient and a preset electricity price base to establish an electricity price calculation function; the electricity price calculation module is also used to calculate the current electricity price based on the selected electricity price coefficient using the electricity price calculation function; an early warning module, used to issue an early warning message based on the current electricity price.

[0024] Compared with the prior art, the present invention has the following advantages:

[0025] 1. The present invention establishes a carbon emission prediction model and uses it to predict carbon emissions, thereby obtaining relatively accurate carbon emission prediction values. The model is trained and optimized based on multi-dimensional information such as historical carbon emission data, historical meteorological data, and historical power generation data of coal-fired power plants, thereby improving the accuracy of the prediction.

[0026] 2. The present invention establishes an electricity price coefficient linked to the predicted carbon emissions, so that electricity prices can dynamically reflect carbon emissions. When the predicted carbon emissions are high, a higher electricity price coefficient is selected, thereby increasing the operating costs of power generation companies and incentivizing them to reduce carbon emissions.

[0027] 3. Compared with traditional fixed electricity prices or electricity price mechanisms that are simply linked to electricity consumption, the electricity price mechanism of the present invention is more flexible and targeted. It can dynamically adjust the electricity price base and electricity price coefficient based on factors such as economic indicators, electricity demand, and power plant operating data in different regions, making the electricity price more in line with actual market conditions and environmental protection policy requirements;

[0028] 4. The present invention achieves real-time monitoring and early warning of carbon emissions and electricity prices by establishing an electricity price calculation function and a carbon emission prediction model. This helps to promptly identify potential problems and risks, take appropriate management measures for intervention and adjustment, and improve management efficiency.

[0029] 5. By linking electricity prices to carbon emissions, the present invention encourages power generation companies to adopt more efficient power generation technologies and cleaner energy, thereby reducing carbon emission intensity; it helps promote the green development of the coal-fired power generation industry and promote sustainable economic development.

[0030] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 It is a flow chart of a provincial coal-fired power generation carbon emission monitoring and management method according to an embodiment of the present invention.

[0033] Figure 2 4 is a flow chart of a carbon emission prediction model optimization method according to an embodiment of the present invention.

[0034] Figure 3 This is a flowchart of an execution method for monitoring and managing carbon emissions from coal-fired power generation in a provincial area according to an embodiment of the present invention.

[0035] Figure 4 4 is a flowchart of a method for optimizing the first threshold and the second threshold according to an embodiment of the present invention.

[0036] Figure 5 It is a schematic diagram of a provincial coal-fired power generation carbon emission monitoring and management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0038] Reference Figure 1 An embodiment of the present invention proposes a provincial coal-fired power generation carbon emission monitoring and management method. Through a management mechanism that links electricity prices with carbon emissions, it can achieve accurate monitoring and effective management of provincial coal-fired power generation carbon emissions.

[0039] The method of this embodiment specifically includes:

[0040] Using the preset electricity price coefficient and the preset electricity price base, the electricity price calculation function is established. For the electricity price p,

[0041] p=μ*D,

[0042] Wherein, μ is the electricity price coefficient, and D is the electricity price base;

[0043] Establishing a carbon emission prediction model, and using the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value;

[0044] Selecting the electricity price coefficient according to the magnitude of the carbon emission prediction value, the electricity price coefficient including a first coefficient, a second coefficient and a third coefficient;

[0045] According to the selected electricity price coefficient, the current electricity price is calculated using the electricity price calculation function, and an early warning message is issued.

[0046] Specifically, based on the calculated current electricity price, an early warning message will be issued; the purpose of the early warning message is to allow relevant parties (such as regulatory authorities, power plants, etc.) to understand the current electricity price situation in a timely manner so that they can take corresponding measures; the content of the early warning message may include the specific value of the current electricity price, the trend of electricity price changes, possible influencing factors, etc.

[0047] Specifically, an electricity price calculation function is established through a preset electricity price coefficient and an electricity price base, and combined with a carbon emission prediction model to achieve accurate monitoring and effective management of carbon emissions from coal-fired power generation. This method not only improves the accuracy of carbon emission predictions, but also incentivizes enterprises to reduce carbon emissions through the linkage mechanism between electricity prices and carbon emissions, which helps promote the green development of the coal-fired power generation industry.

[0048] Optionally, the establishing of an electricity price calculation function using a preset electricity price coefficient and a preset electricity price base includes:

[0049] Collect historical operating data of coal-fired power plants, local historical economic indicators, historical electricity demand data, and historical electricity prices to obtain the first training set;

[0050] Specifically, we collect the operating data of coal-fired power plants over the past period of time, including power generation, coal consumption, equipment operating status, etc.; collect local economic indicator data, such as GDP growth rate, industrial added value, residents' income level, etc., which can reflect the local economic vitality and electricity demand potential; record the electricity demand situation over the past period of time, including electricity consumption and electricity load in different time periods (such as seasons, months, and days); collect electricity price data over the past period of time, which are the basis for training the electricity price base prediction model; by collecting the above data, we can construct the first training set, which contains all the input and output data required to establish the electricity price base prediction model.

[0051] Taking historical operating data of coal-fired power plants, local historical economic indicators, and historical electricity demand data as input and historical electricity prices as output, a neural network model is established and trained using the first training set to obtain an electricity price base prediction model;

[0052] Specifically, a neural network model is used to establish an electricity price base prediction model, with historical operating data of coal-fired power plants, local historical economic indicators and historical electricity demand data as input, and historical electricity prices as output. The neural network model is trained using a first training set; by continuously adjusting the model parameters, the model's prediction results are made as close as possible to the actual electricity price; after training, an electricity price base prediction model is obtained, which can predict the current electricity price base based on current operating data, economic indicators and electricity demand data.

[0053] Collect current operating data of coal-fired power plants, local economic indicators, and current electricity demand data to obtain a basic data set for electricity prices;

[0054] The electricity price basic data set is input into the electricity price base prediction model to obtain the current electricity price base.

[0055] For example, suppose there is a coal-fired power plant in a certain province, and it is necessary to establish an electricity price calculation function for it; the operating data of the power plant in the past year, the local economic indicator data, electricity demand data and electricity price data in the past year are collected; these data are organized into the first training set to train the electricity price base prediction model; a three-layer neural network model is selected as the electricity price base prediction model; the data in the first training set are divided into a training set and a validation set, and the model is trained and validated; after multiple iterative training, the prediction accuracy of the model on the validation set reaches a high level; currently, the operating data of the power plant has been collected Data (such as daily power generation of 1 million kWh, coal consumption of 500 tons, etc.), local economic indicator data (such as GDP growth rate of 5%, industrial added value growth of 8%, etc.) and electricity demand data (such as the daily electricity consumption forecast of 900,000 kWh, etc.); these data are organized into an electricity price basic data set and input into the trained electricity price base prediction model; the model outputs the current electricity price base, for example, it can be 0.45 yuan / kWh; assuming that the second coefficient is selected as the electricity price coefficient based on the carbon emission forecast value, the second coefficient can be 1.2, then the current electricity price is 1.2X0.45=0.54 yuan / kWh.

[0056] Optionally, establishing a carbon emission prediction model includes:

[0057] Collect historical carbon emission data, historical meteorological data, and historical power generation data from coal-fired power plants to construct a comprehensive factor dataset;

[0058] Specifically, historical carbon emission data include records of carbon emissions from coal-fired power plants over a period of time in the past. These data reflect the carbon emissions of power plants under different operating conditions. Meteorological conditions, such as temperature, humidity, and wind speed, have a significant impact on carbon emissions from coal-fired power plants. Therefore, collecting historical meteorological data is crucial to improving the accuracy of carbon emission forecasts. There is a direct relationship between power generation and carbon emissions. Collecting historical power generation data helps understand the carbon emission characteristics of power plants under different power generation loads. By integrating the above data, a data set containing comprehensive factors is constructed. These data sets will provide data support for subsequent model training.

[0059] Preprocessing the comprehensive factor data set to obtain a second training set;

[0060] Specifically, outliers and missing values ​​in the data set are removed to ensure the accuracy and completeness of the data; different types of data are normalized or standardized to improve the efficiency and accuracy of model training; features that have a significant impact on carbon emission prediction are selected from the comprehensive factor data set, or feature extraction techniques (such as principal component analysis) are used to reduce data dimensions and improve model performance; the data set after these preprocessing is called the second training set, which will be used for subsequent model training.

[0061] The second training set is used to establish and train a neural network model to obtain a carbon emission prediction model.

[0062] Specifically, a neural network model with two hidden layers can be selected as the carbon emission prediction model. The data in the second training set is divided into a training set and a validation set, and the model is trained and verified. During the training process, cross-validation technology is used to evaluate the performance of the model, and the parameters of the model are continuously adjusted to improve the prediction accuracy. After the training is completed, a neural network model that can predict future carbon emissions is obtained. Through the above steps, a neural network model that can predict provincial coal-fired power generation carbon emissions is successfully established, which not only improves the accuracy of carbon emission predictions, but also provides strong support for subsequent carbon emission management and electricity price adjustments.

[0063] Optionally, the using the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value includes:

[0064] Collect current carbon emission data, current meteorological data, and current power generation data of coal-fired power plants to obtain real-time data sets;

[0065] The real-time data set is input into the carbon emission prediction model to obtain a carbon emission prediction value.

[0066] For example, assume there is a coal-fired power plant in a certain province, for which a carbon emissions prediction model has been established. Current carbon emissions data for the power plant are obtained in real time through online monitoring equipment, assuming it is 500 tons / hour. Current meteorological data, including temperature of 25°C, humidity of 60%, and wind speed of 3 meters / second, is obtained from the local weather station. Current power generation data, assuming it is 1 million kilowatt-hours / hour, is obtained through the power plant's monitoring system. These data are integrated to form a real-time dataset. This real-time dataset is input into a trained carbon emissions prediction model, which may have been trained based on historical data from the past few years and can identify the impact of factors such as power generation and meteorological conditions on carbon emissions. After receiving the real-time dataset, the model performs complex calculations and analysis. Based on the model's internal algorithms and parameters, it predicts that under current conditions, the power plant's future carbon emissions could be 510 tons / hour. The resulting carbon emissions prediction value can be used in subsequent carbon emissions management and electricity price adjustments, such as implementing emission reduction measures or adjusting electricity price strategies to incentivize power plants to reduce carbon emissions.

[0067] Alternatively, as Figure 2 As shown, the method further includes:

[0068] Collect actual carbon emissions from coal-fired power plants;

[0069] Specifically, in practical applications, it is necessary to regularly collect the actual carbon emissions values ​​of coal-fired power plants; these actual values ​​can be obtained through online monitoring equipment, emission testing, or third-party verification; the purpose of collecting actual values ​​is to compare them with the predicted values ​​of the model to evaluate the accuracy of the model.

[0070] Calculate the error between actual carbon emissions and predicted carbon emissions;

[0071] Specifically, the actual carbon emission value is compared with the predicted carbon emission value, and the error between them is calculated; the error can be an absolute error (i.e., the absolute value of the difference between the actual value and the predicted value) or a relative error (i.e., the ratio of the error to the actual value); the size of the error reflects the accuracy of the model prediction. The smaller the error, the more accurate the model prediction.

[0072] When the error is greater than a preset error threshold, a back propagation algorithm is used to iteratively optimize the parameters in the carbon emission prediction model;

[0073] Specifically, when the error is greater than the preset error threshold, it means that the prediction accuracy of the model needs to be improved. At this time, the backpropagation algorithm can be used to optimize the model. The backpropagation algorithm is a commonly used neural network optimization algorithm. It calculates the gradient of the error and then adjusts the model parameters in the opposite direction of the gradient to reduce the error. During the optimization process, the training data set can be repeatedly used to iteratively train the model until the error is less than or equal to the preset error threshold or the number of iterations reaches the upper limit.

[0074] When the error is less than or equal to the error threshold or the number of iterations reaches an upper limit, the optimization is stopped to obtain a final carbon emission prediction model.

[0075] Specifically, when the error is less than or equal to the preset error threshold, it means that the prediction accuracy of the model has met the requirements. At this time, the optimization can be stopped to obtain the final carbon emission prediction model; if the number of iterations reaches the upper limit but the error is still greater than the preset error threshold, the optimization can also be stopped, but it should be noted that the prediction accuracy of the model may still need to be improved.

[0076] For example, assume that there is a coal-fired power plant in a certain province, and a carbon emission prediction model has been established for it; in the past month, the actual carbon emission values ​​of the power plant have been collected regularly, for example, once a day, and a total of 30 actual values ​​have been collected; these 30 actual values ​​are compared with the predicted values ​​of the model, and the absolute error between them is calculated; assuming that the preset error threshold is 10 tons / hour, after calculation, it is found that the error on some days exceeds this threshold, indicating that the prediction accuracy of the model needs to be improved; when it is found that the error is greater than the preset error threshold, the back propagation algorithm is used to optimize the model, and the historical data of the past year is selected as the training data set, and the model is iteratively trained. In each iteration, the gradient of the error is calculated, and the parameters of the model are adjusted in the opposite direction of the gradient; after multiple iterations, it is found that the error gradually decreases and is eventually less than or equal to the preset error threshold; when the error is less than or equal to the preset error threshold, the optimization process is stopped, and the final carbon emission prediction model is obtained.

[0077] Alternatively, as Figure 3 As shown, the selection of the electricity price coefficient according to the size of the carbon emission prediction value includes:

[0078] Determining whether the predicted carbon emission value is greater than a preset first threshold;

[0079] Specifically, the carbon emission forecast value represents the future carbon emissions of a coal-fired power plant. By predicting carbon emissions, the environmental performance of the power plant can be evaluated and the electricity price coefficient adjusted accordingly. The electricity price coefficient is a parameter used to adjust electricity prices. By changing the electricity price coefficient, the revenue of the power plant can be affected, thereby incentivizing it to reduce carbon emissions. In order to reasonably judge the carbon emission forecast value and select the corresponding electricity price coefficient, multiple thresholds need to be preset. These thresholds can be set according to policy goals, environmental protection standards and the actual situation of the power plant.

[0080] If the predicted carbon emission value is greater than the first threshold, selecting the first coefficient;

[0081] Specifically, first determine whether the carbon emission prediction value is greater than the preset first threshold. If it is, it means that the carbon emissions of the power plant are high and more stringent electricity price adjustment measures are needed. Therefore, the first coefficient is selected (usually a smaller coefficient used to reduce the electricity price).

[0082] If the predicted carbon emission value is less than or equal to the first threshold, determining whether the predicted carbon emission value is greater than a second threshold;

[0083] If the predicted carbon emission value is greater than the second threshold, selecting the second coefficient;

[0084] Specifically, if the predicted carbon emission value is less than or equal to the first threshold, it is further determined whether it is greater than the second threshold; if it is greater, it means that the carbon emissions of the power plant are at a medium level and certain electricity price adjustment measures need to be taken, so the second coefficient is selected (usually a moderate coefficient used to moderately adjust the electricity price).

[0085] If the predicted carbon emission value is less than or equal to the second threshold, the third coefficient is selected.

[0086] Specifically, if the predicted carbon emission value is less than or equal to the second threshold, it means that the carbon emission of the power plant is low and has reached a good environmental protection standard, so the third coefficient is selected (usually a higher coefficient used to increase the electricity price).

[0087] For example, suppose there is a coal-fired power plant in a certain province, and we hope to incentivize it to reduce carbon emissions by adjusting electricity prices; suppose the preset first threshold is 1000 tons / hour and the second threshold is 800 tons / hour; through the carbon emission prediction model, the future carbon emission forecast value of the power plant is obtained to be 900 tons / hour; first, determine whether the carbon emission forecast value (900 tons / hour) is greater than the first threshold (1000 tons / hour). Since 900 tons / hour is less than 1000 tons / hour, the condition is not met; then, determine whether the carbon emission forecast value (900 tons / hour) is greater than the second threshold ( 800 tons / hour), since 900 tons / hour is greater than 800 tons / hour, the condition is met; according to the judgment result, the second coefficient is selected as the electricity price coefficient, assuming that the second coefficient is 1.2 (that is, the electricity price is increased by 20% on the original basis); according to the selected electricity price coefficient (1.2), the electricity price of the power plant is adjusted, for example, if the original electricity price is 0.5 yuan / kWh, the adjusted electricity price is 0.6 yuan / kWh; through such a mechanism, carbon emissions can be closely combined with electricity prices, and power plants can be encouraged to reduce carbon emissions through electricity price adjustments, thereby achieving the dual goals of environmental protection and economic benefits.

[0088] Alternatively, as Figure 4 As shown, the method further includes:

[0089] Collect historical carbon emission data from various coal-fired power plants and calculate the median carbon emission;

[0090] Specifically, it is necessary to collect historical carbon emission data from each coal-fired power plant. These data may include carbon emissions and carbon emission intensity over a period of time in the past. The median carbon emission data collected can be used to calculate the median carbon emission. The median is a statistic that indicates that in a set of data, half of the data values ​​are smaller than it and half of the data values ​​are larger than it. Choosing the median as a reference point can reduce the impact of extreme values ​​on the results.

[0091] Obtain carbon emission target values ​​from a preset database;

[0092] Specifically, a carbon emission target value is obtained from a preset database; this target value may be set by a regulatory agency to guide power plants to achieve long-term goals in reducing carbon emissions.

[0093] The first threshold value is calculated using the carbon emission target value and the carbon emission median. For the first threshold value x1,

[0094] x1=c1(m*Z+n*G)+k1,

[0095] Wherein, c1 is the coefficient of variation of the first threshold, m is the weight coefficient of the median carbon emissions, Z is the median carbon emissions, n is the weight coefficient of the carbon emission target value, G is the carbon emission target value, and k1 is the error coefficient of the second threshold;

[0096] The second threshold value is calculated using the carbon emission target value and the carbon emission median. For the second threshold value x2,

[0097] x2=c2*(m*Z+n*G)-k2,

[0098] Wherein, c2 is the variation coefficient of the second threshold, and k2 is the error coefficient of the second threshold.

[0099] For example, assuming that the median carbon emissions is 900 tons / hour, the carbon emissions target is 800 tons / hour, the variation coefficient of the first threshold is 1.1, the variation coefficient of the second threshold is 0.9, the weight coefficient of the median carbon emissions is 0.6, the weight coefficient of the carbon emissions target is 0.4, the error coefficient of the first threshold is 50, and the error coefficient of the second threshold is 30; the first threshold x1 is calculated according to the formula: 1.1×(0.6×900+0.4×800)+50=996 tons / hour; the first threshold x1 is calculated according to the formula: The second threshold x2 = 0.9 × (0.6 × 900 + 0.4 × 800) - 30 = 744 tons / hour; therefore, based on these parameters and formulas, the calculated first threshold is 996 tons / hour and the second threshold is 744 tons / hour; these thresholds can be used in subsequent electricity price adjustment mechanisms to incentivize power plants to reduce carbon emissions; if the carbon emissions of a power plant are lower than the second threshold, a higher electricity price can be obtained; if the carbon emissions are higher than the first threshold, a higher electricity price will need to be paid or other penalties will be faced.

[0100] Alternatively, as Figure 4 As shown, the method further includes:

[0101] Collect carbon emission and operating data of coal-fired power plants and calculate the carbon emission and operating change rates;

[0102] Specifically, it is necessary to collect carbon emission data and operating data from coal-fired power plants. Carbon emission data can include annual carbon emissions and carbon emission intensity; operating data can include power generation, sales revenue, costs, etc. Calculating the difference between the total carbon emissions of the current year and the total carbon emissions of the previous year directly reflects the annual changes in the power plant's carbon emissions; calculating the difference between the operating data of the current year and the operating data of the previous year (for example, the difference in power generation or sales revenue) directly reflects the annual changes in the power plant's operations.

[0103] The risk assessment value is calculated using the carbon emission change rate and the operating change rate. For the risk assessment value f, there is

[0104] f=α*T+β*Q+λ,

[0105] In the formula, α is the weight coefficient of the carbon emission change rate, T is the carbon emission change rate, β is the weight coefficient of the operating change rate, Q is the operating data, and λ is the error coefficient.

[0106] For example, assuming that the carbon emission change rate is 0.1 (indicating that the carbon emissions are 10% different from the previous year), the operating change rate is 0.05 (indicating that the sales revenue is 5% different from the previous year), the weight coefficient of the carbon emission change rate is 0.6, the weight coefficient of the operating change rate is 0.4, and the error coefficient is 0.01; the risk assessment value is calculated according to the formula f = 0.6×0.1+0.4×0.05+0.01=0.09; the risk level of the power plant is evaluated by judging the risk assessment value. When the operation or carbon emissions change greatly (indicating that these changes have a greater impact on coal-fired enterprises), the carbon emission threshold is adjusted to re-judge the electricity price coefficient.

[0107] Alternatively, as Figure 4 As shown, the method further includes:

[0108] When the risk assessment value is greater than a preset third threshold, determining whether the risk assessment value is greater than a preset fourth threshold;

[0109] Specifically, first, the carbon emission data and operating data of the coal-fired power plant are collected, the carbon emission change rate and the operating change rate are calculated, and these change rates are used to calculate the risk assessment value. This risk assessment value reflects the comprehensive risk level of the power plant in terms of carbon emissions and operations; when the risk assessment value is greater than the preset third threshold, it means that the power plant is currently facing a high level of risk, and its carbon emission threshold or carbon emission target value may need to be adjusted; next, it is further determined whether the risk assessment value is greater than the preset fourth threshold.

[0110] If not, adjusting the variation coefficient of the first threshold, the error coefficient of the first threshold, the variation coefficient of the second threshold, and the error coefficient of the second threshold;

[0111] Specifically, if the risk assessment value is not greater than the fourth threshold, the variation coefficient of the first threshold, the error coefficient of the first threshold, the variation coefficient of the second threshold, and the error coefficient of the second threshold are adjusted; the adjustment of these coefficients can affect the calculation of the carbon emission threshold, and then adjust the selection of the electricity price coefficient, thereby indirectly affecting the behavior of the power plant.

[0112] If so, the carbon emission target value is adjusted.

[0113] Specifically, if the risk assessment value is greater than the fourth threshold, it is considered that the risk faced by the power plant is extremely high and the carbon emission target value needs to be adjusted directly; the adjustment of the carbon emission target value is a more direct and significant means that can directly affect the carbon emission behavior of the power plant.

[0114] For example, suppose there is a coal-fired power plant in a certain province with carbon emission data of 10 million tons this year and 9 million tons last year; operating data of power generation this year is 50 billion kWh, last year was 45 billion kWh, sales revenue this year is 2 billion yuan, last year was 1.8 billion yuan; carbon emission change rate is 0.11, operating change rate (taking power generation as an example) is 0.11; assuming the weight coefficient of carbon emission change rate is 0.6, the weight coefficient of operating change rate is 0.4, and the error coefficient is 0.01; the risk assessment value is f = 0.6×0.11+0.4×0.11-0.01=0.11; assuming the third threshold is 0.1 , the fourth threshold is 0.15. Since the risk assessment value of 0.11 is greater than the third threshold of 0.1, further judgment is required. Since the risk assessment value of 0.11 is not greater than the fourth threshold of 0.15, it is decided to adjust the correlation coefficient of the carbon emission threshold; for example, the variation coefficient of the first threshold is adjusted from 1.1 to 1.05, and the variation coefficient of the second threshold is adjusted from 0.9 to 0.95, so as to slightly relax the carbon emission threshold and give the power plant a certain buffer space; through this process, the present invention can dynamically adjust the carbon emission threshold or carbon emission target value according to the risk level of the power plant, thereby achieving more refined and effective management of carbon emissions from coal-fired power generation.

[0115] Based on the same inventive concept, Figure 5 As shown, the present invention also provides a provincial coal-fired power generation carbon emission monitoring and management system, the system comprising:

[0116] A carbon emission prediction module is used to establish a carbon emission prediction model and use the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value;

[0117] An electricity price coefficient selection module, configured to select the electricity price coefficient according to the magnitude of the carbon emission prediction value, wherein the electricity price coefficient includes a first coefficient, a second coefficient, and a third coefficient;

[0118] An electricity price calculation module is used to establish an electricity price calculation function using a preset electricity price coefficient and a preset electricity price base; the electricity price calculation module is further used to calculate the current electricity price using the electricity price calculation function according to the selected electricity price coefficient;

[0119] The early warning module is used to issue early warning information according to the current electricity price.

[0120] It should be noted that the electrical connections between the above-mentioned units do not necessarily mean direct connections of lines. Indirect connections are applicable to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above description is only an exemplary embodiment of the present invention and is not intended to limit the scope of the present invention.

[0121] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. Those skilled in the art will readily conceive of other embodiments of the present invention after considering the disclosure of the specification and practical truths. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary technical means in the art not described herein.

Claims

1. A provincial coal-fired power generation carbon emission monitoring and management method, characterized by: The method comprises: Using the preset electricity price coefficient and the preset electricity price base, the electricity price calculation function is established. ,have ， Where, is the electricity price coefficient, is the electricity price base; Establishing a carbon emission prediction model and using the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value; the method includes: collecting current carbon emission data, current meteorological data, and current power generation data of the coal-fired power plant to obtain a real-time data set; inputting the real-time data set into the carbon emission prediction model to obtain a carbon emission prediction value; The electricity price coefficient is selected according to the size of the carbon emission prediction value, and the electricity price coefficient includes a first coefficient, a second coefficient, and a third coefficient; the method includes: judging whether the carbon emission prediction value is greater than a preset first threshold; if the carbon emission prediction value is greater than the first threshold, selecting the first coefficient; if the carbon emission prediction value is less than or equal to the first threshold, judging whether the carbon emission prediction value is greater than a second threshold; if the carbon emission prediction value is greater than the second threshold, selecting the second coefficient; if the carbon emission prediction value is less than or equal to the second threshold, selecting the third coefficient; According to the selected electricity price coefficient, the current electricity price is calculated using the electricity price calculation function, and an early warning message is issued; The optimization of the carbon emission prediction model includes: collecting actual carbon emission values ​​of coal-fired power plants; calculating the error between the actual carbon emission values ​​and the carbon emission prediction values; when the error is greater than a preset error threshold, using a backpropagation algorithm to iteratively optimize the parameters in the carbon emission prediction model; stopping the optimization when the error is less than or equal to the error threshold or the number of iterations reaches an upper limit, thereby obtaining the final carbon emission prediction model; Wherein, obtaining the first threshold and the second threshold comprises: collecting historical carbon emission data of each coal-fired power plant and calculating the median carbon emission; obtaining the carbon emission target value from a preset database; using the carbon emission target value and the carbon emission median to calculate the first threshold, and for the first threshold ,have ， Where, is the coefficient of variation of the first threshold, is the weight coefficient of the median carbon emission, is the median carbon emission, is the weight coefficient of the carbon emission target value, is the carbon emission target value, is the error coefficient of the second threshold; the second threshold is calculated using the carbon emission target value and the carbon emission median, and for the second threshold ,have ， Where, is the coefficient of variation of the second threshold, is the error coefficient of the second threshold.

2. A provincial coal-fired power generation carbon emission monitoring and management method according to claim 1, characterized in that: The method of establishing an electricity price calculation function using a preset electricity price coefficient and a preset electricity price base includes: Collect historical operating data of coal-fired power plants, local historical economic indicators, historical electricity demand data, and historical electricity prices to obtain the first training set; Taking historical operating data of coal-fired power plants, local historical economic indicators, and historical electricity demand data as input and historical electricity prices as output, a neural network model is established and trained using the first training set to obtain an electricity price base prediction model; Collect current operating data of coal-fired power plants, local economic indicators, and current electricity demand data to obtain a basic data set for electricity prices; The electricity price basic data set is input into the electricity price base prediction model to obtain the current electricity price base.

3. The provincial coal-fired power generation carbon emission monitoring and management method according to claim 1 is characterized in that: The establishing of the carbon emission prediction model comprises: Collect historical carbon emission data, historical meteorological data, and historical power generation data from coal-fired power plants to construct a comprehensive factor dataset; Preprocessing the comprehensive factor data set to obtain a second training set; The second training set is used to establish and train a neural network model to obtain a carbon emission prediction model.

4. The provincial coal-fired power generation carbon emission monitoring and management method according to claim 1 is characterized in that: The method further comprises: Collect carbon emission and operating data of coal-fired power plants and calculate the carbon emission and operating change rates; The risk assessment value is calculated using the carbon emission change rate and the operating change rate. ,have ， Where, is the weight coefficient of the carbon emission change rate, is the carbon emission change rate, is the weight coefficient of the operating change rate, For the said operating data, is the error coefficient.

5. A provincial coal-fired power generation carbon emission monitoring and management method according to claim 4, characterized in that: The method further comprises: When the risk assessment value is greater than a preset third threshold, determining whether the risk assessment value is greater than a preset fourth threshold; If not, adjusting the variation coefficient of the first threshold, the error coefficient of the first threshold, the variation coefficient of the second threshold, and the error coefficient of the second threshold; If so, the carbon emission target value is adjusted.

6. A provincial coal-fired power generation carbon emission monitoring and management system, applied to the provincial coal-fired power generation carbon emission monitoring and management method according to any one of claims 1 to 5, characterized in that: The system comprises: A carbon emission prediction module is used to establish a carbon emission prediction model and use the carbon emission prediction model to predict carbon emissions to obtain a carbon emission prediction value. This includes: collecting current carbon emission data, current meteorological data, and current power generation data of the coal-fired power plant to obtain a real-time data set; inputting the real-time data set into the carbon emission prediction model to obtain a carbon emission prediction value; An electricity price coefficient selection module is configured to select the electricity price coefficient according to the size of the predicted carbon emission value, the electricity price coefficient including a first coefficient, a second coefficient, and a third coefficient; the module includes: determining whether the predicted carbon emission value is greater than a preset first threshold; if the predicted carbon emission value is greater than the first threshold, selecting the first coefficient; if the predicted carbon emission value is less than or equal to the first threshold, determining whether the predicted carbon emission value is greater than a second threshold; if the predicted carbon emission value is greater than the second threshold, selecting the second coefficient; if the predicted carbon emission value is less than or equal to the second threshold, selecting the third coefficient; An electricity price calculation module is used to establish an electricity price calculation function using a preset electricity price coefficient and a preset electricity price base; the electricity price calculation module is further used to calculate the current electricity price using the electricity price calculation function according to the selected electricity price coefficient; An early warning module, configured to issue early warning information according to the current electricity price; The optimization of the carbon emission prediction model includes: collecting actual carbon emission values ​​of coal-fired power plants; calculating the error between the actual carbon emission values ​​and the carbon emission prediction values; when the error is greater than a preset error threshold, using a backpropagation algorithm to iteratively optimize the parameters in the carbon emission prediction model; stopping the optimization when the error is less than or equal to the error threshold or the number of iterations reaches an upper limit, thereby obtaining the final carbon emission prediction model; Among them, obtaining the first threshold and the second threshold includes: collecting historical carbon emission data of each coal-fired power plant and calculating the median carbon emission; obtaining the carbon emission target value from a preset database; using the carbon emission target value and the carbon emission median to calculate the first threshold; using the carbon emission target value and the carbon emission median to calculate the second threshold.

Images