New energy and pumped storage combined power generation system full life cycle carbon emission evaluation method

Abstract

The invention discloses a new energy and pumped storage combined power generation system full life cycle carbon emission evaluation method, and relates to the technical field of power system carbon footprints. Comprising the following steps: firstly, obtaining and preprocessing carbon emission data of a new energy power station including a wind power station, a photovoltaic station and a pumped storage power station, and generating a training sample data set; then, a neural network model is established based on the data set, and training is carried out by taking power station construction feature data including the material consumption, the transportation distance and the equipment number as input and taking the carbon emission as a label; and then, inputting construction characteristic data and environmental parameters of the power station to be evaluated, and correcting a carbon emission predicted value. And finally, in combination with the dynamic growth index of the load demand of the power grid, calculating the full-life-cycle carbon emission, and realizing accurate evaluation. The method has the characteristics of systematicness, intellectualization and data driving, and is suitable for carbon emission management and optimization of a new energy and pumped storage combined power generation system.

Description

Technical Field

[0001] This invention relates to the field of carbon footprint technology for power systems, specifically a method for assessing carbon emissions throughout the entire life cycle of a combined renewable energy and pumped storage power generation system. Background Technology

[0002] With increasing global concern about climate change and environmental protection, developing low-carbon, sustainable energy systems has become a crucial task for research institutions. Traditional fossil fuel power generation not only generates substantial greenhouse gas emissions but also causes numerous environmental problems, such as air pollution and ecological damage. To address these issues, the development and utilization of new energy sources have gradually become mainstream, especially the rapid development of renewable energy sources such as wind power and solar photovoltaic power. However, the intermittency and instability of new energy power generation pose challenges to their application in power systems. This necessitates the use of other power systems, such as pumped-storage hydroelectric power plants, to achieve power balancing and dispatch.

[0003] Pumped storage hydroelectric power stations, as a mature energy storage technology, can utilize surplus electricity to pump water for energy storage when electricity demand is low, and release the stored energy during peak demand periods to balance the grid load. However, despite their important role in regulating power supply, pumped storage hydroelectric power stations also involve carbon emissions during their construction and operation, especially in equipment manufacturing, material transportation, and power station construction. Existing methods often focus only on a single power source or power station, lacking a systematic assessment of the full life-cycle carbon emissions of combined renewable energy and pumped storage power generation systems.

[0004] Furthermore, existing carbon emission assessment methods typically rely on static data or rough estimates, lacking a dynamic response to changes in environmental parameters. Carbon emissions from power plants can vary significantly under different climatic conditions and geographical environments. Therefore, a comprehensive assessment method is urgently needed to accurately predict and assess the carbon emissions throughout the entire lifecycle of combined renewable energy and pumped storage power generation systems, taking into account various external and internal factors.

[0005] In the prior art, CN117151481A discloses a method and apparatus for assessing the carbon emissions of a wind-solar-storage combined power generation system throughout its entire life cycle. The method includes: first, determining the carbon emission system boundary of the wind-solar-storage combined power generation system; then, dividing the entire life cycle into stages based on the life cycle theory in project management; next, determining the carbon emission inventory for each stage to obtain the total carbon emission inventory generated by the wind-solar-storage combined power generation system throughout its entire life cycle; and finally, determining the total carbon emissions generated by the wind-solar-storage combined power generation system throughout its entire life cycle based on the total carbon emission inventory. This method clearly defines the carbon footprint of the wind-solar-storage combined power generation system and can accurately calculate the total carbon dioxide emissions throughout its entire life cycle. However, this method fails to fully consider the dynamic impact of environmental conditions on carbon emissions, such as the influence of climate change, temperature, and humidity on wind and solar power generation efficiency. These factors can significantly change power generation and carbon emissions. Furthermore, it does not consider the dynamic changes in carbon emissions with electricity demand. Therefore, the accuracy and effectiveness of the assessment method are reduced.

[0006] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to provide a method for assessing carbon emissions throughout the entire life cycle of a new energy and pumped storage combined power generation system, so as to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: A method for assessing the carbon emissions of a combined renewable energy and pumped storage power generation system throughout its entire life cycle, comprising the following steps: A predictive model is constructed with power plant type and power plant construction feature data as inputs and output as total life cycle carbon emissions. Power plant construction feature data and total life cycle carbon emissions of several different types of power plants are obtained for model training. The total life cycle carbon emissions include the total carbon emissions during the equipment manufacturing stage, power plant construction stage, and waste recycling stage, as well as the total carbon emissions during the power plant operation stage. The power plant construction feature data includes the type and amount of power plant construction materials, construction transportation distance, recycling transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance operations, and corresponding single maintenance type and single maintenance time. Data on the type and construction characteristics of each power station in the new energy and pumped storage combined power generation system to be evaluated are obtained and input into the trained prediction model to obtain the predicted value of carbon emissions throughout the life cycle of each power station. The total number of maintenance times and the corresponding single maintenance type and single maintenance time data are used as the average value of the collected sample data as the input to the model. At the same time, environmental parameters of the location of the new energy and pumped storage combined power generation system to be evaluated are obtained. These environmental parameters include the average temperature, average humidity, average wind speed, average solar radiation intensity, and average rainfall over the past five years. Based on the collected environmental parameters, the predicted total carbon emissions during the power plant's operation phase are corrected to obtain the actual environmental emission correction value. At the same time, the growth rate of grid user-side load demand and the current load demand are obtained. Based on the obtained growth rate of grid user-side load demand and the current load demand, a dynamic growth index is calculated. Based on the actual environmental emission correction value and the dynamic growth index, the total life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated are calculated to complete the total life cycle carbon emission assessment.

[0009] Furthermore, the power station types include pumped storage power stations, wind power stations, and photovoltaic power stations, wherein the carbon emission data for each life cycle are preprocessed, and the preprocessing includes dimensionless preprocessing and normalization preprocessing. The training data of the prediction model is stored in the training sample dataset. The method for generating the training sample dataset is as follows: the preprocessed carbon emission data is mapped one-to-one with the corresponding power plant construction feature data to form a corresponding grid, and the resulting grid is recorded as the training sample dataset.

[0010] Furthermore, based on the data in the training sample dataset, a neural network model is established, specifically an LSTM model. An activation function and optimization algorithm are selected, with the Tanh function chosen as the activation function and Adam as the optimization algorithm for the LSTM model. The formula for the Tanh function is: ; In the formula, Represents the Tanh function, with the independent variable... This represents the weighted sum of the neuron's inputs, that is, the result of the weighted sum of the inputs received by the neuron from the previous layer; Simultaneously, the hyperparameters of the LSTM model are set, including: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons. The network is set to a 4-layer structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, the number of batches is set to 256, and the number of hidden layer neurons is set to 32. The input to the trained carbon emission prediction model is the power plant construction feature data, including the type and amount of power plant construction materials, construction transportation distance, recycling transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance and corresponding single maintenance type and single maintenance time. The output is the total carbon emission prediction value for different stages of the corresponding power plant, of which the carbon emission prediction value for the power plant operation stage is the total carbon emission prediction value for different types of power plants. Specifically, the predicted total carbon emissions for different stages of the power plant, output by the model, characterize the predicted total emissions for the remaining stages excluding the power plant operation phase. The specific formula used for the calculation is as follows: ; In the formula, , and These are the predicted total emissions from pumped-storage power plants, wind power plants, and photovoltaic power plants for the remaining phases excluding the power plant operation phase. , and These are the predicted total emissions during the equipment manufacturing stages of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These are the predicted total emissions during the construction phase of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These are the predicted total emissions during the waste recycling phase of pumped storage power plants, wind power plants, and photovoltaic power plants, respectively.

[0011] Furthermore, the predicted carbon emissions during the power plant operation phase are corrected based on the collected environmental parameters to obtain the corrected actual environmental emissions. The specific formula used to obtain the accurate actual environmental emissions is as follows: ; In the formula, For the combined renewable energy and pumped storage power generation system to be evaluated, the total carbon emissions during the power plant's operational phase are as follows. , , These are the actual total environmental emissions correction values ​​for wind power plants, photovoltaic power plants, and pumped storage power plants in the new energy and pumped storage combined power generation system to be evaluated.

[0012] Among them, the actual environmental emission correction value of wind power stations The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted total carbon emissions of a wind power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This is a temperature correction factor. This is the humidity correction factor; The annual average wind speed at the location of the combined renewable energy and pumped storage power generation system to be evaluated is used. For reference wind speed; Among them, the actual environmental emission correction value of photovoltaic power plants The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted carbon emissions of a photovoltaic power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This represents the annual average intensity of solar radiation. For reference solar radiation intensity.

[0013] Furthermore, the actual environmental emission correction values ​​for pumped storage power stations The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted carbon emissions of a pumped storage power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. The average annual rainfall, For reference rainfall.

[0014] Furthermore, the total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment are calculated based on the accurate actual environmental emissions and dynamic growth index. The specific formula used for calculating the total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment is as follows: ; in, To assess the lifecycle carbon emissions of the combined renewable energy and pumped storage power generation system, It is a dynamic growth index. This represents the total predicted carbon emissions for the k-th power plant type, excluding the power plant operation phase, for the remaining phases, where k is the index of the power plant type, and the dynamic growth index is... The specific formula used for the calculation is as follows: ; In the formula, This represents the increase in grid user-side load demand compared to the previous year. This represents the current load demand.

[0015] Compared with the prior art, the beneficial effects of the present invention are: First, by acquiring data from each key stage, the carbon emission characteristics of new energy power plants and pumped storage power plants throughout their entire life cycle can be comprehensively and meticulously revealed. Incorporating carbon emissions from all stages, including equipment production, material transportation, power plant construction, production maintenance, and waste recycling, ensures the comprehensiveness and accuracy of the assessment. Second, using neural network models from machine learning to predict carbon emissions, and training them with characteristic data from power plants, allows the model to adapt to the characteristics of different power plants, thereby improving the accuracy of the prediction. Through big data analysis and model optimization, complex nonlinear relationships can be effectively handled, making the assessment results more reliable. Furthermore, this scheme also considers the impact of environmental parameters, making the carbon emission assessment more dynamic and adaptable. By analyzing factors such as annual average temperature, humidity, wind speed, solar radiation intensity, and rainfall, carbon emissions during the power plant operation phase can be corrected, thereby improving the accuracy of the assessment. Simultaneously, the introduction of a dynamic growth index allows the carbon emission assessment to reflect changes in grid user-side load demand in real time, characterizing the carbon emission growth trend, ultimately improving the accuracy and effectiveness of carbon emission assessments for new energy power plants and pumped storage power plants throughout their entire life cycle. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall method flow of the present invention; Figure 2 A bar chart showing the statistical accuracy of carbon emission forecasts; Figure 3 A comparison chart of corrected values ​​for the total life cycle carbon emissions of different types of power plants. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0018] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Example: Please see Figures 1-3 The present invention provides a technical solution: A method for assessing the carbon emissions of a combined renewable energy and pumped storage power generation system throughout its entire life cycle, comprising the following steps: Step 1: Construct a prediction model that takes power plant type and power plant construction feature data as input and outputs total life cycle carbon emissions. Obtain power plant construction feature data and total life cycle carbon emissions for several different types of power plants for model training. The total life cycle carbon emissions include the total carbon emissions during the equipment manufacturing stage, power plant construction stage, and waste recycling stage, as well as the total carbon emissions during the power plant operation stage. The power plant construction feature data includes the type and quantity of power plant construction materials, construction transportation distance, recycling transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance operations, and corresponding single maintenance type and single maintenance time.

[0020] The power plant types include pumped storage power plants, wind power plants, and photovoltaic power plants. The acquired carbon emission data for each life cycle undergoes preprocessing, which includes dimensionless preprocessing and normalization preprocessing. Specifically, the normalization preprocessing scales the carbon emission parameters for each life cycle within their corresponding maximum range.

[0021] The training data of the prediction model is stored in the training sample dataset. The method for generating the training sample dataset is as follows: the preprocessed carbon emission data is mapped one-to-one with the corresponding power plant construction feature data to form a corresponding grid, and the resulting grid is recorded as the training sample dataset.

[0022] The process can be divided into four phases: equipment manufacturing (including the manufacturing of all equipment such as wind turbines, photovoltaic modules, and water pumps, as well as the transportation of equipment and materials from the manufacturing site to the construction site); power plant construction (including civil engineering and equipment installation); power plant operation (including maintenance, management, and energy production during operation); and waste disposal (including the dismantling and recycling of equipment and materials). By combining industry research and reports, carbon emission data for specific power plants and regions can be obtained to provide more accurate estimates.

[0023] Step 2: Obtain the type and construction characteristics data of each power station in the new energy and pumped storage combined power generation system to be evaluated, and input them into the completed prediction model to obtain the predicted value of carbon emissions throughout the entire life cycle of each power station. The total number of maintenance times and the corresponding single maintenance type and single maintenance time data are used as the average value of the collected sample data as the input to the model.

[0024] Among them, the planned power generation of the new energy and pumped storage combined power generation system to be evaluated is used as the total power generation. The planned power generation is the planned power generation of the new energy and pumped storage combined power generation system to be evaluated during its service life.

[0025] Based on the data in the training sample dataset, a neural network model is built, specifically an LSTM model. An activation function and optimization algorithm are selected: Tanh is chosen as the activation function, and Adam is chosen as the optimization algorithm for the LSTM model. The formula for the Tanh function is: ; In the formula, Represents the Tanh function, with the independent variable... This represents the weighted sum of the neuron's inputs, that is, the result of the weighted sum of the inputs received by the neuron from the previous layer; Simultaneously, the hyperparameters of the LSTM model are set, including: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons. The network is set to a 4-layer structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, the number of batches is set to 256, and the number of hidden layer neurons is set to 32. The input to the trained carbon emission prediction model is the power plant construction feature data, including the type and amount of power plant construction materials, construction and transportation distance, recycling and transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance and corresponding single maintenance type and single maintenance time. The output is the total carbon emission prediction value for different stages of the corresponding power plant, of which the carbon emission prediction value for the power plant operation stage is the total carbon emission prediction value for different types of power plants. Specifically, the predicted total carbon emissions for different stages of the power plant, output by the model, characterize the predicted total emissions for the remaining stages excluding the power plant operation phase. The specific formula used for the calculation is as follows: ; In the formula, , and These are the predicted total emissions from pumped-storage power plants, wind power plants, and photovoltaic power plants for the remaining phases excluding the power plant operation phase. , and These are the predicted total emissions during the equipment manufacturing stages of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These are the predicted total emissions during the construction phase of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These figures represent the predicted total emissions from the waste recovery phases of pumped-storage power plants, wind power plants, and photovoltaic power plants, respectively. The predicted total emissions for each phase are the sum of carbon emissions from the same type of power plant.

[0026] Among them, the LSTM model can flexibly adapt to the input of different feature data. For power plant construction feature data, such as production material consumption, transportation distance, and number of equipment, LSTM can automatically learn the relationships and influences between different features without the need for manual design of feature interactions. This adaptive characteristic makes LSTM perform better in modeling complex systems.

[0027] When building carbon emission prediction models, many factors, such as equipment status, maintenance history, and the use of production materials, can affect the final carbon emissions. LSTM can comprehensively consider these multiple input features and automatically extract important features through its complex network structure, which helps to improve the accuracy of predictions.

[0028] Carbon emissions are typically influenced by a variety of time-dependent factors, such as seasonal variations, economic cycles, and policy adjustments. LSTMs are effective at capturing these time dependencies. Through their unique memory unit structure, LSTMs can remember past information and decide when to forget irrelevant information, making them particularly effective when processing time series data. Many changes in carbon emissions are caused by long-term trends or cyclical factors, such as the gradual implementation of energy policies or the cumulative effect of technological progress. Traditional neural networks (such as standard RNNs) may encounter the vanishing gradient problem when dealing with long-term dependencies, while LSTMs, through their gating mechanism, can retain important information over longer time series, thus better adapting to long-term trends in carbon emissions.

[0029] Many power plants and related companies use ERP systems to manage information such as production, procurement, inventory, and equipment maintenance. By accessing these systems, detailed data such as production material usage, equipment quantity, and maintenance records can be obtained. During power plant operation, staff can regularly record relevant data, especially the number of maintenance visits and the duration of each maintenance visit. Table 1 shows the statistical values ​​of the prediction accuracy of some of the prediction models after training.

[0030] Table 1: Partial Statistics on Prediction Accuracy of the Prediction Model

[0031] The data in Table 1 aims to analyze the accuracy of the prediction model and the relationship between actual and predicted data. The prediction accuracy of all samples ranges from 80% to 91.25%, with an average accuracy of approximately 88.50%. This indicates that the prediction model has a certain degree of reliability overall, but attention still needs to be paid to individual samples with lower accuracy.

[0032] Step 3: Simultaneously obtain the environmental parameters of the location of the new energy and pumped storage combined power generation system to be evaluated. The environmental parameters include the average temperature, average humidity, average wind speed, average solar radiation intensity and average rainfall over the past five years.

[0033] Among the power plant construction characteristic data of the new energy and pumped storage combined power generation system to be evaluated, the number of maintenance and the time of a single maintenance are taken as the average number of maintenance and the time of a single maintenance from the collected sample data as the input of the model.

[0034] Specific methods for obtaining environmental parameters include: accessing the official website of the China Meteorological Administration to obtain meteorological data for various regions, including annual average temperature, humidity, and wind speed. Some professional meteorological data platforms, such as WeatherUnderground and NASA's Climate Data Center, provide historical meteorological data, allowing users to query required environmental parameters based on specific locations and time periods. Local meteorological observatories typically have detailed meteorological observation records; data can be obtained by consulting relevant local meteorological departments. Satellite remote sensing technology can also be used to acquire environmental parameter data. For example, the Medium Resolution Imaging Spectroradiometer (MRISC) and the Sentinel satellite both provide various types of climate and environmental data.

[0035] If there is no readily available meteorological data in the required data area, it is advisable to build a meteorological station in the target area to monitor and record environmental parameters in real time, including temperature, humidity, wind speed, and rainfall.

[0036] Step 4: Based on the collected environmental parameters, the predicted total carbon emissions during the power plant operation phase are corrected to obtain the actual environmental emission correction value. At the same time, the growth rate of grid user-side load demand and the current load demand are obtained. Based on the obtained growth rate of grid user-side load demand and the current load demand, the dynamic growth index is calculated. Based on the actual environmental emission correction value and the dynamic growth index, the total life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated are calculated to complete the total life cycle carbon emission assessment.

[0037] The predicted carbon emissions during the power plant's operation phase are corrected based on the collected environmental parameters to obtain the corrected actual environmental emissions. The specific formula used to obtain the accurate actual environmental emissions is as follows: ; In the formula, For the combined renewable energy and pumped storage power generation system to be evaluated, the total carbon emissions during the power plant's operational phase are as follows. , , These are the actual total environmental emissions correction values ​​for wind power plants, photovoltaic power plants, and pumped storage power plants in the new energy and pumped storage combined power generation system to be evaluated.

[0038] Among them, the actual environmental emission correction value of wind power stations The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted total carbon emissions of a wind power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This is a temperature correction factor. This is the humidity correction factor. For reference wind speed; Temperature correction coefficient The specific value selection logic is as follows: when hour, Take 0.2; when hour, Take 0.4; when hour, Take 0.2; when hour, Take 0.4; when hour, Set to 0; Among them, temperature correction coefficient Specifically, this indicates the impact of temperature differences on carbon emissions, when the actual temperature differs from the reference temperature. The greater the difference, the higher the temperature correction factor. The larger the value, the greater the impact of temperature on the correction of total carbon emissions. The specific logic is as follows: temperature affects the efficiency and mechanical performance of power generation equipment. High temperatures may cause equipment to overheat, thus affecting power generation efficiency and indirectly increasing carbon emissions. In low-temperature environments, friction in the mechanical components of the power plant increases, thereby reducing the operating efficiency of the power plant. Low temperatures may also cause ice and snow to adhere to the power plant equipment, increasing wind resistance and reducing the power generation capacity of the wind turbines, thus affecting the overall power generation efficiency. Therefore... The average annual temperature of the location of the new energy and pumped storage combined power generation system to be evaluated Compared with reference temperature The absolute value of the difference is proportional. Wherein, the reference temperature... The corresponding values ​​are set according to the different types of power plants.

[0039] Humidity correction factor The specific value selection logic is as follows: when hour, Take 0.2; when hour, Take 0.4; when hour, Take 0.2; when hour, Take 0.4; when hour, Set to 0; Among them, humidity correction factor Indicates when the ambient humidity is different from the reference humidity The degree of impact on power plant carbon emissions under different differences varies; the greater the difference between ambient humidity and reference humidity, the larger the humidity correction factor. The higher the value, the greater the impact on the power plant's carbon emissions. The specific logic for determining the value is as follows: High humidity increases the water content in the air, putting pressure on the cooling system and operating environment of the power generation equipment. Decreased cooling efficiency leads to increased equipment temperature and reduced operating efficiency. Simultaneously, high humidity environments easily cause corrosion of equipment, especially reducing the insulation performance of metal components and electrical equipment, accelerating equipment aging and increasing the failure rate. Furthermore, excessive humidity can lead to microbial growth or pollutant deposition, adversely affecting power generation equipment, further reducing power generation efficiency and increasing carbon emissions. Low humidity also affects the normal operation of the power plant. Low humidity environments easily lead to static electricity buildup, interfering with the stability of electrical equipment and increasing the risk of equipment failure. In long-term operation, low humidity may also accelerate the aging or performance degradation of certain materials, affecting equipment lifespan and operational stability. (Reference humidity...) Compared with reference temperature Similarly, different values ​​are set according to different types of power plants.

[0040] To determine the average annual temperature of the location where the new energy and pumped storage combined power generation system to be evaluated is located, The average annual humidity of the location where the new energy and pumped storage combined power generation system to be evaluated is located.

[0041] It is important to note that wind speed is a key factor affecting wind power generation efficiency. Changes in wind speed directly affect the rotor speed and generator output power, thus influencing carbon emissions. Increased wind speed leads to a non-linear increase in power output, thereby improving power generation efficiency and indirectly reducing carbon emissions per unit of electricity. Therefore, the actual environmental emission correction value for wind power stations... and The effect of wind speed variation is inversely proportional to the carbon emissions. Using a logarithmic function to handle this variation can reflect, to some extent, the non-linear impact of wind speed changes on carbon emissions. Higher wind speeds typically increase the power generation efficiency of wind turbines, potentially reducing carbon emissions per unit of electricity.

[0042] Among them, the actual environmental emission correction value of photovoltaic power plants The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted carbon emissions of a photovoltaic power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This represents the annual average intensity of solar radiation. For reference solar radiation intensity.

[0043] It should be noted that the impact of humidity is similar to that described above. Regarding the impact of temperature, photovoltaic power plants require direct sunlight, and the operating environment is generally quite warm. Temperature changes have a relatively small impact on the power generation efficiency and carbon emissions of photovoltaic power plants, and therefore will not be considered here. Therefore... It is directly proportional to the average annual humidity of the location where the new energy and pumped storage combined power generation system to be evaluated is located.

[0044] Solar radiation intensity is the most direct influencing factor on photovoltaic power generation. Variations in radiation under different times and weather conditions directly affect power output and carbon emissions. Higher radiation intensity results in higher power generation efficiency for photovoltaic panels and relatively lower carbon emissions. Therefore, the annual average solar radiation intensity... and Inversely proportional, through Indicates the annual average intensity of solar radiation Impact on carbon emissions from photovoltaic power plants.

[0045] The actual environmental emission correction value of pumped storage power stations The specific formula used for the calculation is as follows: ; In the formula, This refers to the predicted carbon emissions of a pumped storage power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. The average annual rainfall, For reference rainfall.

[0046] The impact of humidity is similar to that of photovoltaic and wind power plants, and will not be elaborated upon here. Meanwhile, since pumped storage power plants are hydroelectric power plants, and water has a strong ability to regulate temperature, the ambient temperature variation at pumped storage power plants is relatively small. Therefore, temperature changes have a minor impact on the power generation efficiency and carbon emissions of pumped storage power plants and will not be considered here. Thus, average annual rainfall affects the availability of water resources and the water level of reservoirs, thereby affecting the operating efficiency of pumped storage power plants. Higher rainfall usually means a rise in reservoir water levels, which helps the power plant operate more efficiently and may ultimately reduce carbon emissions. Therefore, average annual rainfall... Predicted carbon emissions during the operation phase of a pumped storage power station combining new energy and pumped storage power generation system to be evaluated. Inversely proportional, through It indicates an inverse relationship.

[0047] in , and These are reference temperature, reference humidity, and reference wind speed, respectively. Reference temperature specifically refers to the ambient temperature, which is generally 15 degrees Celsius. Up to 25 Between. Reference humidity is... to The reference wind speed is the local daily minimum wind speed. The reference rainfall is the local annual minimum rainfall, and the reference solar radiation intensity is the local annual minimum solar radiation intensity. The specific settings for reference temperature and reference humidity can be based on the average meteorological data of the area where the sample data was collected, combined with expert experience on the current environment. The settings for reference solar radiation intensity and reference rainfall are similar.

[0048] The total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment are calculated based on the accurate actual environmental emissions and dynamic growth index. The specific formula used for calculating the total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment is as follows: ; in, To assess the lifecycle carbon emissions of the combined renewable energy and pumped storage power generation system, It is a dynamic growth index. This represents the total predicted carbon emissions for the k-th power plant type, excluding the power plant operation phase, for the remaining phases, where k is the index of the power plant type, and the dynamic growth index is... The specific formula used for the calculation is as follows: ; In the formula, This represents the increase in grid user-side load demand compared to the previous year. This represents the current load demand.

[0049] The assessment can be based on a comparison between the lifecycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated and the lifecycle carbon emission threshold. Different assessment results will be issued based on the comparison results. The specific judgment logic is as follows: when At that time, it was determined that the life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated were poor and could not meet the carbon reduction requirements; when If the life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated are judged to be "good", it means that the life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated meet the carbon reduction requirements.

[0050] in The lifecycle carbon emission threshold is obtained by adjusting for the number of power plant devices in the system to be evaluated. The formula used for the calculation is: ; In the formula, This is the initial value for the lifecycle carbon emission threshold. The number of power station equipment in the system to be evaluated. For reference only.

[0051] The more power plant equipment in the system to be evaluated, the higher the carbon emissions will be. Therefore, the life cycle carbon emission threshold should be increased, and a threshold corresponding to the number of equipment should be given.

[0052] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0053] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0055] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for assessing the carbon emissions throughout the entire life cycle of a combined renewable energy and pumped storage power generation system, characterized in that, The specific steps include: A predictive model is constructed with power plant type and power plant construction feature data as inputs and output as total life cycle carbon emissions. Power plant construction feature data and total life cycle carbon emissions of several different types of power plants are obtained for model training. The total life cycle carbon emissions include the total carbon emissions during the equipment manufacturing stage, power plant construction stage, and waste recycling stage, as well as the total carbon emissions during the power plant operation stage. The power plant construction feature data includes the type and amount of power plant construction materials, construction transportation distance, recycling transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance operations, and corresponding single maintenance type and single maintenance time. Data on the type and construction characteristics of each power station in the new energy and pumped storage combined power generation system to be evaluated are obtained and input into the trained prediction model to obtain the predicted value of carbon emissions throughout the life cycle of each power station. The total number of maintenance times and the corresponding single maintenance type and single maintenance time data are used as the average value of the collected sample data as the input to the model. At the same time, environmental parameters of the location of the new energy and pumped storage combined power generation system to be evaluated are obtained. These environmental parameters include the average temperature, average humidity, average wind speed, average solar radiation intensity, and average rainfall over the past five years. Based on the collected environmental parameters, the predicted total carbon emissions during the power plant's operation phase are corrected to obtain the actual environmental emission correction value. At the same time, the growth rate of grid user-side load demand and the current load demand are obtained. Based on the obtained growth rate of grid user-side load demand and the current load demand, a dynamic growth index is calculated. Based on the actual environmental emission correction value and the dynamic growth index, the total life cycle carbon emissions of the new energy and pumped storage combined power generation system to be evaluated are calculated to complete the total life cycle carbon emission assessment.

2. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 1, is characterized in that: The types of power plants include pumped storage power plants, wind power plants, and photovoltaic power plants. The carbon emission data for each life cycle are preprocessed, including dimensionless preprocessing and normalization preprocessing. The training data for the prediction model is stored in the training sample dataset. The method for generating the training sample dataset is as follows: the preprocessed carbon emission data is mapped one-to-one with the corresponding power plant construction feature data to form a corresponding grid, and the resulting grid is recorded as the training sample dataset.

3. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 2, is characterized in that: Based on the data in the training sample dataset, a neural network model is built, specifically an LSTM model. An activation function and optimization algorithm are selected: Tanh is chosen as the activation function, and Adam is chosen as the optimization algorithm for the LSTM model. The formula for the Tanh function is: ； In the formula, Represents the Tanh function, with the independent variable... This represents the weighted sum of the neuron's inputs, that is, the result of the weighted sum of the inputs received by the neuron from the previous layer; Simultaneously, the hyperparameters of the LSTM model are set, including: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons. The network is set to a 4-layer structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, the number of batches is set to 256, and the number of hidden layer neurons is set to 32. The input to the trained carbon emission prediction model is the power plant construction feature data, including the type and amount of power plant construction materials, construction transportation distance, recycling transportation distance, power plant equipment type and quantity, total power generation, total number of maintenance and corresponding single maintenance type and single maintenance time. The output is the total carbon emission prediction value for different stages of the corresponding power plant, of which the carbon emission prediction value for the power plant operation stage is the total carbon emission prediction value for different types of power plants. Specifically, the predicted total carbon emissions for different stages of the power plant, output by the model, characterize the predicted total emissions for the remaining stages excluding the power plant operation phase. The specific formula used for the calculation is as follows: ； In the formula, , and These are the predicted total emissions from pumped-storage power plants, wind power plants, and photovoltaic power plants for the remaining phases excluding the power plant operation phase. , and These are the predicted total emissions during the equipment manufacturing stages of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These are the predicted total emissions during the construction phase of pumped storage power stations, wind power stations, and photovoltaic power stations, respectively. , and These are the predicted total emissions during the waste recycling phase of pumped storage power plants, wind power plants, and photovoltaic power plants, respectively.

4. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 3, is characterized in that: The predicted carbon emissions during the power plant's operation phase are corrected based on the collected environmental parameters to obtain the corrected actual environmental emissions. The specific formula used to obtain the accurate actual environmental emissions is as follows: ； In the formula, For the combined renewable energy and pumped storage power generation system to be evaluated, the total carbon emissions during the power plant's operational phase are as follows. , , These are the actual total environmental emissions correction values ​​for wind power plants, photovoltaic power plants, and pumped storage power plants in the new energy and pumped storage combined power generation system to be evaluated.

5. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 4, is characterized in that: Among them, the actual environmental emission correction value of wind power stations The specific formula used for the calculation is as follows: ； In the formula, This refers to the predicted total carbon emissions of a wind power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This is a temperature correction factor. This is the humidity correction factor; The annual average wind speed at the location of the combined renewable energy and pumped storage power generation system to be evaluated is used. For reference wind speed; Among them, the actual environmental emission correction value of photovoltaic power plants The specific formula used for the calculation is as follows: ； In the formula, This refers to the predicted carbon emissions of a photovoltaic power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. This represents the annual average intensity of solar radiation. For reference solar radiation intensity.

6. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 5, is characterized in that: The actual environmental emission correction value of pumped storage power stations The specific formula used for the calculation is as follows: ； In the formula, This refers to the predicted carbon emissions of a pumped storage power station during the operation phase of a combined renewable energy and pumped storage power generation system to be evaluated. The average annual rainfall, For reference rainfall.

7. The method for assessing the carbon emissions of a combined new energy and pumped storage power generation system throughout its entire life cycle, as described in claim 6, is characterized in that: The total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment are calculated based on the accurate actual environmental emissions and dynamic growth index. The specific formula used for calculating the total life-cycle carbon emissions of the combined renewable energy and pumped storage power generation system under assessment is as follows: ； in, To assess the lifecycle carbon emissions of the combined renewable energy and pumped storage power generation system, It is a dynamic growth index. This represents the total predicted carbon emissions for the k-th power plant type, excluding the power plant operation phase, for the remaining phases, where k is the index of the power plant type, and the dynamic growth index is... The specific formula used for the calculation is as follows: ； In the formula, This represents the increase in grid user-side load demand compared to the previous year. This represents the current load demand.

Images