Renewable energy source configuration method and system based on carbon emission reduction potential

Through the prediction of carbon emission reduction potential of renewable energy units and the application of time-varying CEEMDAN-GRU model of replacing thermal power units, the problems that have not been considered in the carbon emission reduction potential and carbon price factors in the existing technology are solved, and renewable energy is realized The accurate optimization of configuration improves the carbon emission reduction effect and prediction accuracy.

CN119027266AInactive Publication Date: 2024-11-26ECONOMIC & TECH RES INST OF HUBEI ELECTRIC POWER COMPANY SGCC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410890257.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing renewable energy allocation method fails to effectively consider the potential of carbon emission reduction and carbon price factors, resulting in the failure to accurately reflect the impact of carbon emission fluctuations and returns, affecting the accuracy of the forecast results and the returns of renewable energy projects.

Method used

A renewable energy allocation method based on carbon emission reduction potential is proposed. By predicting the carbon emission reduction potential of renewable energy units instead of thermal power units, and building an optimized configuration model based on the predicted value, using the time-varying CEEMDAN-GRU model to carbon Forecasting emission reduction potential, combining dynamic carbon emission reduction potential and carbon price to build a renewable energy optimized allocation model with the goal of maximizing returns.

Benefits of technology

It realizes the precise quantification of the carbon emission reduction effect of renewable energy substitute thermal power units, improves the rationality and accuracy of the prediction results, supports the formulation of configuration plans to maximize the carbon emission reduction effect, and uses small prediction errors and high specimen Combining the advantages of energy companies and investors has improved the decision-making capabilities of energy companies and investors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027266A_ABST
    Figure CN119027266A_ABST
Patent Text Reader

Abstract

The invention discloses a renewable energy source configuration method and system based on carbon emission reduction potential, and the method comprises the steps: carrying out the prediction of the carbon emission reduction potential of a renewable energy source unit replacing a thermal power unit, and constructing a renewable energy source optimal configuration model with the maximum renewable energy source configuration benefit as the target based on a carbon emission reduction potential prediction value. And then solving the renewable energy optimal configuration model to obtain a renewable energy configuration scheme. According to the method, the possible carbon emission reduction effect in the substitution process can be accurately quantified, a renewable energy source configuration scheme for maximizing the carbon emission reduction effect is supported and formulated, and the reasonability and accuracy of a prediction result are effectively guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of power grid planning, and in particular relates to a renewable energy configuration method and system based on carbon emission reduction potential. Background Art

[0002] The large-scale burning of fossil energy is bound to lead to excessive greenhouse gas emissions. With the continuous increase in global energy demand and the continuous improvement of environmental protection awareness, the development of renewable energy, as an environmentally friendly and infinitely available energy form, is expected to provide clean and sustainable energy solutions for the world. By formulating a scientific and reasonable renewable energy allocation strategy, it will not only help the healthy development of the new energy industry, but also help power companies achieve a win-win situation in terms of economic and environmental benefits.

[0003] At present, conventional renewable energy allocation methods either do not consider carbon emission reduction potential and carbon price factors, or consider these factors as stable and unchanging factors, which cannot reflect the impact of carbon emission fluctuations and carbon price fluctuations on the benefits of renewable energy projects brought about by renewable energy allocation. At the same time, undifferentiated carbon emission reduction potential and carbon price will also affect the accuracy of prediction results at different time scales. Summary of the invention

[0004] The purpose of the present invention is to provide a renewable energy configuration method and system based on carbon emission reduction potential in view of the above-mentioned problems existing in the prior art.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] In a first aspect, the present invention proposes a renewable energy configuration method based on carbon emission reduction potential, comprising:

[0007] S1. Predict the carbon emission reduction potential of renewable energy units replacing thermal power units;

[0008] S2. Based on the predicted value of carbon emission reduction potential, a renewable energy optimization configuration model is constructed with the goal of maximizing the benefits of renewable energy configuration;

[0009] S3. Solve the renewable energy optimization configuration model and obtain the renewable energy configuration plan.

[0010] The S1 includes:

[0011] S11. With T as the time span of each period, determine the carbon emission reduction potential time series including the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period based on historical data, wherein the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period is calculated according to the following formula:

[0012]

[0013] In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units;

[0014] S12. Perform empirical mode decomposition on the carbon emission reduction potential time series to obtain N IMF components with different frequencies and 1 residual component;

[0015] S13. Input each component obtained into the constructed GRU neural network model for training and prediction, and obtain the prediction result of each component. The prediction results of all components are superimposed to obtain the predicted value of carbon emission reduction potential of renewable energy units replacing thermal power units.

[0016] The S11, CE kT,i It is calculated using the following formula:

[0017]

[0018] In the above formula, p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t;

[0019] The CF kT,i It is calculated using the following formula:

[0020]

[0021] In the above formula, E all The carbon emissions of the whole life cycle of the project of replacing thermal power units with renewable energy, Q i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit;

[0022] The CP kT It is calculated using the following formula:

[0023]

[0024] In the above formula, PP kT,jis the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, and y(t) is the carbon price curve during the carbon price fluctuation period.

[0025] The S12 includes:

[0026] S121. Add Gaussian white noise to the carbon emission reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ;

[0027] S122. Take an overall average of the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition. cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component;

[0028] S123. Add positive and negative paired Gaussian white noise to r1(t) to obtain a new signal, and use EMD to decompose the new signal to obtain the second-order intrinsic mode component C emd2 ;

[0029] S124. Perform an overall average on the second-order eigenmode component to obtain the second eigenmode component C of CEEMDAN decomposition. cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component;

[0030] S125, repeat steps S123-S124 in a loop until the obtained residual signal is a monotonic function and cannot be further decomposed. At this time, S(t) is decomposed into:

[0031]

[0032] In the above formula, N is the number of IMF components, C ceen (t), r n (t) are the nth eigenmode component and the residual component after removing the nth eigenmode component.

[0033] In S2, the objective function of the renewable energy optimization configuration model includes:

[0034] maxW net =(W new -W the +W car +W gov )

[0035]

[0036] In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit.

[0037] The constraints of the renewable energy optimization configuration model include:

[0038] Revenue cycle constraints:

[0039] 0≤T≤T life

[0040] Where, T life Lifespan of projects to replace thermal power units with renewable energy

[0041] Renewable energy unit capacity constraints:

[0042] 0≤Q i ≤Q MAX

[0043] In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units;

[0044] Power generation constraints of thermal power units:

[0045] P i,min ≤P i (t)≤P i,max

[0046] In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

[0047] In a second aspect, the present invention proposes a renewable energy configuration system based on carbon emission reduction potential, including a carbon emission reduction potential prediction module, a renewable energy optimization configuration model construction module, and a renewable energy optimization configuration model solution module;

[0048] The carbon emission reduction potential prediction module is used to predict the carbon emission reduction potential of renewable energy units replacing thermal power units;

[0049] The renewable energy optimization configuration model construction module is used to construct a renewable energy optimization configuration model with the goal of maximizing renewable energy configuration benefits based on the carbon emission reduction potential prediction value;

[0050] The renewable energy optimization configuration model solving module is used to solve the renewable energy optimization configuration model to obtain a renewable energy configuration plan.

[0051] The carbon emission reduction potential prediction module includes a time series determination unit, an empirical mode decomposition unit, and a training and prediction unit;

[0052] The time series determination unit is used to determine the carbon emission reduction potential time series including the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period based on historical data, with T as the time span of each period, wherein the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period is calculated according to the following formula:

[0053]

[0054]

[0055] In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units, and p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t, E all The carbon emissions of the whole life cycle of the project of replacing thermal power units with renewable energy, Q i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,iis the average service life of the i-th renewable energy unit, PP kT,j is the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, and y(t) is the carbon price curve during the carbon price fluctuation period;

[0056] The empirical mode decomposition unit is used to perform empirical mode decomposition on the carbon emission reduction potential time series to obtain N IMF components with different frequencies and 1 residual component;

[0057] The training and prediction unit is used to input each component obtained by the empirical mode decomposition unit into the constructed GRU neural network model for training and prediction, obtain the prediction result of each component, and superimpose the prediction results of all components to obtain the carbon emission reduction potential prediction value of the renewable energy unit replacing the thermal power unit.

[0058] The empirical mode decomposition unit performs empirical mode decomposition on the carbon emission reduction potential time series based on the following steps:

[0059] A. Add Gaussian white noise to the carbon reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ;

[0060] B. Take an overall average of the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component;

[0061] C. Add positive and negative paired Gaussian white noise to r1(t) to get a new signal, and use EMD to decompose the new signal to get the second-order intrinsic mode component C emd2 ;

[0062] D. Take an overall average of the second-order eigenmode components to obtain the second eigenmode component C of CEEMDAN decomposition cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component;

[0063] E. Repeat steps CD until the residual signal is a monotonic function and cannot be decomposed further. At this time, S(t) is decomposed into:

[0064]

[0065] In the above formula, N is the number of IMF components, C ceen (t), r n(t) are the nth eigenmode component and the residual component after removing the nth eigenmode component.

[0066] The objective function of the renewable energy optimization configuration model includes:

[0067] maxW net =(W new -W the +W car +W gov )

[0068]

[0069] In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit;

[0070] The constraints of the renewable energy optimization configuration model include:

[0071] Revenue cycle constraints:

[0072] 0≤T≤T life

[0073] Where, T life Lifespan of projects to replace thermal power units with renewable energy

[0074] Renewable energy unit capacity constraints:

[0075] 0≤Q i ≤Q MAX

[0076] In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units;

[0077] Power generation constraints of thermal power units:

[0078] P i,min ≤P i (t)≤P i,max

[0079] In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

[0080] Compared with the prior art, the present invention has the following beneficial effects:

[0081] 1. A renewable energy configuration method based on carbon emission reduction potential proposed in the present invention first predicts the carbon emission reduction potential of renewable energy units replacing thermal power units, then constructs a renewable energy optimization configuration model with the goal of maximizing the renewable energy configuration benefit based on the predicted value of carbon emission reduction potential, and then solves the renewable energy optimization configuration model to obtain a renewable energy configuration plan. On the one hand, this method proposes a carbon emission reduction potential indicator for renewable energy units replacing thermal power units, and incorporates it into the renewable energy optimization configuration model, which can accurately quantify the carbon emission reduction effect that may be achieved during the replacement process, and helps energy companies and investors to more accurately understand the potential and value of renewable energy in reducing carbon emissions, and support the formulation of a renewable energy configuration plan that maximizes the carbon emission reduction effect; on the other hand, this method adopts a dynamic carbon emission reduction potential value and carbon price, which effectively ensures the rationality and accuracy of the prediction results.

[0082] 2. The present invention proposes a renewable energy configuration method based on carbon emission reduction potential, which adopts the time-varying CEEMDAN-GRU model to predict the carbon emission reduction potential of renewable energy units replacing thermal power units, including empirical mode decomposition of the carbon emission reduction potential time series based on the CEEMDAN algorithm, and training and predicting each component obtained by the decomposition based on the GRU neural network model. This method has smaller prediction error and higher goodness of fit by adding a limited number of adaptive white noises. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 This is a flow chart of the method described in Example 1.

[0084] Figure 2 This is a structural diagram of the system described in Example 2. DETAILED DESCRIPTION

[0085] The present invention is further described in detail below in conjunction with specific implementations and drawings.

[0086] Embodiment 1:

[0087] like Figure 1 As shown, a renewable energy configuration method based on carbon emission reduction potential is implemented in the following steps:

[0088] 1. With T as the time span of each period, determine the carbon emission reduction potential time series including the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period based on historical data, where the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period is calculated according to the following formula:

[0089]

[0090] In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units, and p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t. This parameter is calculated in real time based on the power flow. all The carbon emissions of the entire life cycle of the project of replacing thermal power units with renewable energy include carbon emissions in the raw material acquisition and processing stage, carbon emissions in the equipment manufacturing stage, carbon emissions in the material and equipment transportation stage, carbon emissions in the project construction stage, carbon emissions in the operation and maintenance stage, and carbon emissions in the recycling and disposal stage. i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit, PP kT,j is the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, which is determined by the accuracy of the prediction results, and y(t) is the carbon price curve during the carbon price fluctuation period.

[0091] 2. Perform empirical mode decomposition on the carbon emission reduction potential time series to obtain N IMF components with different frequencies and 1 residual component, including:

[0092] 2.1. Add Gaussian white noise to the carbon reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ;

[0093] 2.2. Take an overall average of the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component;

[0094] 2.3. Add positive and negative paired Gaussian white noise to r1(t) to get a new signal, and use EMD to decompose the new signal to get the second-order intrinsic mode component C emd2 ;

[0095] 2.4. Take an overall average of the second-order eigenmode components to obtain the second eigenmode component C of CEEMDAN decomposition cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component;

[0096] 2.5. Repeat steps 2.3-2.4 until the residual signal obtained is a monotonic function and cannot be further decomposed. At this time, S(t) is decomposed into:

[0097]

[0098] In the above formula, N is the number of IMF components, C ceen (t), r n (t) are the nth eigenmode component and the residual component after removing the nth eigenmode component.

[0099] 3. Divide the decomposed component data into training sets and test sets. Select the first 75% of the data as the training set and the last 25% of the data as the test set. Use the GRU neural network model for training and prediction to obtain the prediction results of each component. Superimpose the prediction results of all components to obtain the predicted value of carbon emission reduction potential of renewable energy units replacing thermal power units.

[0100] 4. Based on the predicted value of carbon emission reduction potential, the following renewable energy optimization configuration model is constructed with the goal of maximizing the benefits of renewable energy configuration:

[0101] Objective function:

[0102] maxW net =(W new -W the +W car +W gov )

[0103]

[0104] In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit;

[0105] Constraints:

[0106] Revenue cycle constraints

[0107] 0≤T≤T life

[0108] Where, T life Lifespan of projects to replace thermal power units with renewable energy

[0109] Renewable energy unit capacity constraints

[0110] 0≤Q i ≤Q MAX

[0111] In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units;

[0112] Power Constraints of Thermal Power Units

[0113] P i,min ≤P i (t)≤P i,max

[0114] In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

[0115] 5. Solve the above renewable energy optimization configuration model to obtain the renewable energy configuration plan, including renewable energy configuration time and configuration capacity.

[0116] Embodiment 2:

[0117] like Figure 2 As shown, a renewable energy configuration system based on carbon emission reduction potential includes a carbon emission reduction potential prediction module, a renewable energy optimization configuration model construction module, and a renewable energy optimization configuration model solution module.

[0118] The carbon emission reduction potential prediction module is used to predict the carbon emission reduction potential of renewable energy units replacing thermal power units, and includes a time series determination unit, an empirical mode decomposition unit, and a training and prediction unit;

[0119] The time series determination unit is used to determine the carbon emission reduction potential time series including the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period based on historical data, with T as the time span of each period, wherein the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period is calculated according to the following formula:

[0120]

[0121] In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units, and p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t. This parameter is calculated in real time based on the power flow. all The carbon emissions of the entire life cycle of the project of replacing thermal power units with renewable energy include carbon emissions in the raw material acquisition and processing stage, carbon emissions in the equipment manufacturing stage, carbon emissions in the material and equipment transportation stage, carbon emissions in the project construction stage, carbon emissions in the operation and maintenance stage, and carbon emissions in the recycling and disposal stage. i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit, PP kT,jis the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, which is determined by the accuracy of the prediction result, and y(t) is the carbon price curve during the carbon price fluctuation period;

[0122] The empirical mode decomposition unit is used to perform empirical mode decomposition on the carbon emission reduction potential time series based on the following steps to obtain N IMF components with different frequencies and 1 residual component:

[0123] A. Add Gaussian white noise to the carbon reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ;

[0124] B. Take an overall average of the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component;

[0125] C. Add positive and negative paired Gaussian white noise to r1(t) to get a new signal, and use EMD to decompose the new signal to get the second-order intrinsic mode component C emd2 ;

[0126] D. Take an overall average of the second-order eigenmode components to obtain the second eigenmode component C of CEEMDAN decomposition cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component;

[0127] E. Repeat steps CD until the residual signal is a monotonic function and cannot be decomposed further. At this time, S(t) is decomposed into:

[0128]

[0129] In the above formula, N is the number of IMF components, C ceen (t), r n (t) are the nth eigenmode component and the residual component after removing the nth eigenmode component;

[0130] The training and prediction unit is used to input each component obtained by the empirical mode decomposition unit into the constructed GRU neural network model for training and prediction, obtain the prediction result of each component, and superimpose the prediction results of all components to obtain the carbon emission reduction potential prediction value of the renewable energy unit replacing the thermal power unit.

[0131] The renewable energy optimization configuration model construction module is used to construct a renewable energy optimization configuration model with the goal of maximizing renewable energy configuration benefits based on the carbon emission reduction potential prediction value, wherein the objective function of the renewable energy optimization configuration model includes:

[0132] maxW net =(W new -W the +W car +W gov )

[0133]

[0134] In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit;

[0135] The constraints of the renewable energy optimization configuration model include:

[0136] Revenue cycle constraints:

[0137] 0≤T≤T life

[0138] Where, T life Lifespan of projects to replace thermal power units with renewable energy

[0139] Renewable energy unit capacity constraints:

[0140] 0≤Q i ≤Q MAX

[0141] In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units;

[0142] Power generation constraints of thermal power units:

[0143] P i,min ≤P i (t)≤P i,max

[0144] In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

[0145] The renewable energy optimization configuration model solving module is used to solve the renewable energy optimization configuration model to obtain a renewable energy configuration plan, including renewable energy configuration time and configuration capacity.

Claims

1. A renewable energy configuration method based on carbon emission reduction potential, characterized in that: The method comprises: S1. Predict the carbon emission reduction potential of renewable energy units replacing thermal power units; S2. Based on the predicted value of carbon emission reduction potential, a renewable energy optimization configuration model is constructed with the goal of maximizing the benefits of renewable energy configuration; S3. Solve the renewable energy optimization configuration model and obtain the renewable energy configuration plan.

2. A renewable energy configuration method based on carbon emission reduction potential according to claim 1, characterized in that: The S1 includes: S11. With T as the time span of each period, determine the carbon emission reduction potential time series including the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period based on historical data, wherein the carbon emission reduction potential value of renewable energy units replacing thermal power units in each period is calculated according to the following formula: In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units; S12. Perform empirical mode decomposition on the carbon emission reduction potential time series to obtain N IMF components with different frequencies and 1 residual component; S13. Input each component obtained into the constructed GRU neural network model for training and prediction, and obtain the prediction result of each component. The prediction results of all components are superimposed to obtain the predicted value of carbon emission reduction potential of renewable energy units replacing thermal power units.

3. A renewable energy configuration method based on carbon emission reduction potential according to claim 2, characterized in that: The S11, CE kT,i It is calculated using the following formula: In the above formula, p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t; The CF kT,i It is calculated using the following formula: In the above formula, E all The carbon emissions of the whole life cycle of the project of replacing thermal power units with renewable energy, Q i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit; The CP kT It is calculated using the following formula: In the above formula, PP kT,j is the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, and y(t) is the carbon price curve during the carbon price fluctuation period.

4. A renewable energy configuration method based on carbon emission reduction potential according to claim 2, characterized in that: The S12 includes: S121. Add Gaussian white noise to the carbon emission reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ; S122. Perform an overall average on the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition. cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component; S123. Add positive and negative paired Gaussian white noise to r1(t) to obtain a new signal, and use EMD to decompose the new signal to obtain the second-order intrinsic mode component C emd2 ; S124. Perform an overall average on the second-order eigenmode component to obtain the second eigenmode component C of CEEMDAN decomposition. cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component; S125, repeat steps S123-S124 in a loop until the obtained residual signal is a monotonic function and cannot be further decomposed. At this time, S(t) is decomposed into: In the above formula, N is the number of IMF components, C ceen (t), r n (t) are the nth eigenmode component and the residual component after removing the nth eigenmode component.

5. The renewable energy configuration method based on carbon emission reduction potential according to claim 1, characterized in that: In S2, the objective function of the renewable energy optimization configuration model includes: maxW net =(In new -IN the +W car +W gov ) In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit.

6. A renewable energy configuration method based on carbon emission reduction potential according to claim 5, characterized in that: The constraints of the renewable energy optimization configuration model include: Revenue cycle constraints: 0≤T≤T life Where, T life Lifespan of projects to replace thermal power units with renewable energy Renewable energy unit capacity constraints: 0≤Q i ≤Q MAX In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units; Power generation constraints of thermal power units: P i,min ≤P i (t)≤P i,max In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

7. A renewable energy configuration system based on carbon emission reduction potential, characterized in that: The system includes a carbon emission reduction potential prediction module, a renewable energy optimization configuration model construction module, and a renewable energy optimization configuration model solution module; The carbon emission reduction potential prediction module is used to predict the carbon emission reduction potential of renewable energy units replacing thermal power units; The renewable energy optimization configuration model construction module is used to construct a renewable energy optimization configuration model with the goal of maximizing renewable energy configuration benefits based on the carbon emission reduction potential prediction value; The renewable energy optimization configuration model solving module is used to solve the renewable energy optimization configuration model to obtain a renewable energy configuration plan.

8. A renewable energy configuration system based on carbon emission reduction potential according to claim 7, characterized in that: The carbon emission reduction potential prediction module includes a time series determination unit, an empirical mode decomposition unit, and a training and prediction unit; The time series determination unit is used to determine the carbon emission reduction potential time series including the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period based on historical data, with T as the time span of each period, wherein the carbon emission reduction potential value of the renewable energy unit replacing the thermal power unit in each period is calculated according to the following formula: In the above formula, CPV kT is the carbon emission reduction potential of renewable energy units replacing thermal power units in the kth period, CE kT,i is the carbon emission of the i-th thermal power unit in the k-th period, CF kT,i is the carbon emission in the kth period after the renewable energy unit replaces the i-th thermal power unit, CP kT is the benchmark income that the replaced thermal power units can obtain in the carbon market, S is the number of replaced thermal power units, and p i (t) is the output of the i-th thermal power unit at time t, Φ i (t) is the carbon emission factor of the grid node where the i-th thermal power unit is located at time t, E all The carbon emissions of the whole life cycle of the project of replacing thermal power units with renewable energy, Q i is the capacity of the i-th renewable energy unit, η i is the unit operating efficiency of the i-th renewable energy unit, H i is the annual average full-load generating hours of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit, PP kT,j is the jth carbon price fluctuation value in the kth period, PC i is the capacity of the i-th thermal power unit, T t is the time accuracy of carbon price fluctuation, and y(t) is the carbon price curve during the carbon price fluctuation period; The empirical mode decomposition unit is used to perform empirical mode decomposition on the carbon emission reduction potential time series to obtain N IMF components with different frequencies and 1 residual component; The training and prediction unit is used to input each component obtained by the empirical mode decomposition unit into the constructed GRU neural network model for training and prediction, obtain the prediction result of each component, and superimpose the prediction results of all components to obtain the carbon emission reduction potential prediction value of the renewable energy unit replacing the thermal power unit.

9. A renewable energy configuration system based on carbon emission reduction potential according to claim 7, characterized in that: The empirical mode decomposition unit performs empirical mode decomposition on the carbon emission reduction potential time series based on the following steps: A. Add Gaussian white noise to the carbon reduction potential time series S(t) to obtain a new series S i (t), and use EMD to decompose the new sequence Si(t) to obtain the first-order eigenmode component C emd1 ; B. Take an overall average of the first-order eigenmode component to obtain the first eigenmode component C of CEEMDAN decomposition cee1 (t), and calculate the residual component r1(t) after removing the first eigenmode component; C. Add positive and negative paired Gaussian white noise to r1(t) to get a new signal, and use EMD to decompose the new signal to get the second-order intrinsic mode component C emd2 ; D. Take an overall average of the second-order eigenmode components to obtain the second eigenmode component C of CEEMDAN decomposition cee2 (t), and calculate the residual component r2(t) after removing the second eigenmode component; E. Repeat steps CD until the residual signal is a monotonic function and cannot be decomposed further. At this time, S(t) is decomposed into: In the above formula, N is the number of IMF components, C ceen (t), r n (t) are the nth eigenmode component and the residual component after removing the nth eigenmode component.

10. A renewable energy configuration system based on carbon emission reduction potential according to claim 7, characterized in that: The objective function of the renewable energy optimization configuration model includes: maxW net =(In new -IN the +W car +W gov ) In the above formula, W net Allocate revenue for renewable energy, W new is the net income generated by renewable energy units replacing thermal power units, W the is the power generation income of the thermal power unit before replacement, W car W is the income generated in the carbon market from the reduction of carbon emissions after renewable energy units replace thermal power units. gov The benefits of renewable energy investment incentives, Q i is the capacity of the i-th renewable energy unit, h i is the average utilization hours of the i-th renewable energy unit in each time span T, k is the number of renewable energy units replacing thermal power units, f new,i ,q new,i are the on-grid electricity price and average cost of the i-th renewable energy unit, c i is the average unit cost of investment and construction of the i-th renewable energy unit, T new,i is the average service life of the i-th renewable energy unit; The constraints of the renewable energy optimization configuration model include: Revenue cycle constraints: 0≤T≤T life Where, T life Lifespan of projects to replace thermal power units with renewable energy Renewable energy unit capacity constraints: 0≤Q i ≤Q MAX In the above formula, Q MAX The maximum generating capacity of renewable energy units replacing thermal power units; Power generation constraints of thermal power units: P i,min ≤P i (t)≤P i,max In the above formula, pi(t) is the output of the ith thermal power unit at time t, P i,min , P i,max are the lower and upper limits of the power generation capacity of the i-th generator set respectively.

Citation Information

Patent Citations

  • Capacity optimization configuration method for renewable energy hydrogen production system

    CN115130785A

  • Electricity price prediction method coupled with carbon price

    CN115660724A

  • Emission reduction strategy generation method based on quantitative calculation of enterprise carbon emission reduction potential

    CN116822977A

  • Intelligent wind speed prediction method and system for black start assisted by energy storage

    CN117408164A