Renewable energy consumption potential prediction method based on combined model and application

Abstract

The invention discloses a renewable energy consumption potential prediction method based on a combined model, and the method comprises the steps: obtaining a renewable energy penetration potential index, and carrying out the single-model prediction of the index through a long-short-term memory network model, a multiple linear regression model, a least square support vector machine model, and a random forest model; establishing a combined prediction model based on a single model prediction result, constructing a constraint condition taking a minimum average absolute percentage error as a target function, and introducing a discount factor matrix; a discount factor matrix is optimized through a quantum coding harmony algorithm, a new harmony solution is generated through iteration, and a quantum coding harmony memory bank is updated; and calculating a weight coefficient according to the optimized discount factor matrix, and outputting a joint prediction result of the quantum coding and sound memory library and the combined prediction model. The problems of insufficient multi-factor comprehensive consideration, limited application range of a single model and inconsistent data features in different prediction periods in the existing renewable energy consumption potential prediction can be solved.

Description

Technical Field

[0001] This application relates to the field of energy consumption assessment technology, and in particular to a method for predicting renewable energy consumption potential based on a combined model, a device for predicting renewable energy consumption potential based on a combined model, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Currently, most renewable energy consumption assessments and forecasts employ big data analysis and machine learning methods to construct relevant prediction models. By mining and analyzing a large amount of information such as historical power generation data and grid operation data, high-precision prediction models are trained to predict the renewable energy consumption capacity.

[0003] However, the potential for renewable energy absorption involves multiple factors, and existing models typically only consider some of the main factors, failing to fully incorporate all factors. This makes it difficult for these models to comprehensively and accurately assess the absorption capacity of renewable energy when faced with complex and ever-changing realities. Furthermore, different types of renewable energy, different power system structures, and different operating characteristics require different prediction models. In other words, existing single models often only achieve good prediction results in specific scenarios, and their accuracy and reliability decrease significantly when applied to other scenarios or renewable energy types. Moreover, existing technologies use uniform model parameters and structures for prediction, failing to fully consider the differences in data characteristics across different time periods, making it difficult to meet the needs of real-time and accurate assessment of renewable energy absorption potential in practical applications. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, this invention provides a method and application for predicting renewable energy absorption potential based on a combined model, which can solve the problems of insufficient comprehensive consideration of multiple factors, limited applicability of single models, and inconsistent data characteristics in different prediction periods in existing renewable energy absorption potential prediction methods.

[0005] On one hand, this invention proposes a method for predicting the renewable energy absorption potential based on a combined model, comprising: obtaining a renewable energy penetration potential index; performing single-model predictions on the index using a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model, respectively, to generate single-model prediction results; establishing a combined prediction model based on the single-model prediction results corresponding to each model, and constructing constraints with the objective function of minimizing the mean absolute percentage error, wherein the objective function incorporates a discount factor matrix; optimizing the discount factor matrix using a quantum-encoded harmony algorithm, iteratively generating new harmonic solutions and updating the quantum-encoded harmony memory library until the termination condition is met; calculating weight coefficients based on the optimized discount factor matrix, and outputting the joint prediction result of the quantum-encoded harmony memory library and the combined prediction model.

[0006] In one embodiment of the present invention, the expression of the combined prediction model is: ;in, This represents the combined prediction results for period t. These are the weighting coefficients of individual prediction model i in the combined prediction model. This represents the prediction result of a single prediction model i (i = 1, 2, ..., m) in period t, where m is the number of single prediction models, and its value is 4.

[0007] In one embodiment of the present invention, the formula for calculating the weighting coefficient is: ; in, t is the actual value at time node t, β is the discount factor with a value range of [0, 1], i′ represents the i′-th time node, and T is the number of observation periods.

[0008] In one embodiment of the present invention, the formula for calculating the objective function is: ; in, It is the actual value in period t. It is the predicted value in period t; By introducing the weight coefficients into the expression of the objective function, the constraint expression of the objective function is obtained as follows: .

[0009] In one embodiment of the present invention, the quantum-encoded harmony algorithm includes: setting the harmony memory bank capacity (HMS), harmony memory consideration rate (HMCR), pitch adjustment rate (PAR), and maximum number of iterations; generating an initial harmonious solution through quantum superposition encoding; and generating a new harmonious solution based on the initial harmonious solution through any of the following mechanisms: retaining existing solutions in the QHM, randomly sampling according to the HMCR probability, or performing a small perturbation according to the PAR probability.

[0010] In one embodiment of the present invention, the step of updating the QHM includes: measuring the fitness of the new harmonious solution using MAPE as an evaluation index, and replacing it if the fitness is better than the worst solution in the QHM.

[0011] In one embodiment of the present invention, optimizing the discount factor matrix includes: aiming to minimize the dynamic weighted sum of the prediction errors of each single model in different time periods, so that the data characteristics of the discount factor matrix during the prediction period remain consistent.

[0012] On the other hand, this invention also proposes a renewable energy absorption potential prediction device based on a combined model, comprising: a single-model prediction module for obtaining renewable energy penetration potential indicators, and performing single-model predictions on the indicators using a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model, respectively, to generate single-model prediction results; a combined model building module for building a combined prediction model based on the single-model prediction results corresponding to each model, and constructing constraints with the objective function of minimizing the mean absolute percentage error, wherein the objective function incorporates a discount factor matrix; a discount factor optimization module for optimizing the discount factor matrix using a quantum-encoded harmony algorithm, iteratively generating new harmonic solutions and updating the quantum-encoded harmony memory library until the termination condition is met; and a joint prediction module for calculating weight coefficients based on the optimized discount factor matrix and outputting the joint prediction result of the quantum-encoded harmony memory library and the combined prediction model.

[0013] In another aspect, embodiments of the present invention also propose an electronic device, comprising: a memory and one or more processors connected to the memory, the memory storing a computer program, and the processors being configured to execute the computer program to implement the renewable energy absorption potential prediction method based on a combined model as described in any of the above embodiments.

[0014] In another aspect, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions for performing the renewable energy consumption potential prediction method based on a combined model as described in any of the above embodiments.

[0015] As can be seen from the above, the embodiments of the present invention, compared with the prior art, can have at least one or more of the following beneficial effects: This invention proposes a combined model-based method for predicting renewable energy absorption potential. Addressing the shortcomings of existing models in comprehensively considering multiple factors when assessing renewable energy absorption potential, this method considers several key factors, including the maximum generating capacity of renewable energy, actual generating contribution, grid transmission capacity, and the growth potential of renewable energy. It constructs a multi-factor integrated evaluation index system to accurately measure renewable energy absorption potential. Furthermore, it proposes a combined prediction optimization model based on MDMSFE, leveraging the advantages of each model to form a multi-model integrated prediction architecture. This improves the stability and generalization ability of the prediction results, enabling it to better adapt to different types of renewable energy and diverse power system scenarios. Finally, it introduces a discount factor β into the MDMSFE combined prediction model, using different β values ​​for each individual prediction model and each prediction period. This solves the problems of independent information loss from individual prediction models and inconsistent data characteristics across prediction periods in previous combined prediction models. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings: Figure 1 A flowchart illustrating a method for predicting the renewable energy absorption potential based on a combined model, provided in an embodiment of the present invention; Figure 2 A schematic diagram illustrating the specific execution logic of a renewable energy absorption potential prediction method based on a combined model, provided in an embodiment of the present invention. Figure 3 A schematic diagram of a renewable energy absorption potential prediction device based on a combined model provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described with reference to the accompanying drawings and embodiments.

[0018] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments, and should all fall within the protection scope of the present invention.

[0019] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are applicable in distinguishing similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or applicable to such processes, methods, products, or apparatus.

[0020] It should also be noted that the division of multiple embodiments in this invention is only for the convenience of description and should not constitute a special limitation. Features in various embodiments can be combined and referenced in each other without contradiction.

[0021] like Figure 1 As shown, the first embodiment of the present invention proposes a method for predicting the renewable energy absorption potential based on a combined model, including, for example, the following steps: Step S1, obtaining renewable energy penetration potential indicators, and using a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model to perform single-model predictions on the indicators, generating single-model prediction results; Step S2, establishing a combined prediction model based on the single-model prediction results corresponding to each model, and constructing constraints with minimizing the mean absolute percentage error as the objective function, wherein the objective function introduces a discount factor matrix; Step S3, optimizing the discount factor matrix through a quantum-encoded harmony algorithm, iteratively generating new harmonic solutions and updating the quantum-encoded harmony memory library until the termination condition is met; Step S4, calculating weight coefficients based on the optimized discount factor matrix, and outputting the joint prediction result of the quantum-encoded harmony memory library and the combined prediction model.

[0022] Specifically, in combination Figure 2As shown, in step S1, renewable energy penetration potential indicators are obtained. For example, based on the characteristics of renewable energy penetration potential, the maximum power generation capacity of renewable energy, actual power generation contribution, grid transmission capacity and renewable energy growth potential are comprehensively considered. Renewable energy installed capacity, total renewable energy grid connection, renewable energy access ratio and renewable energy power generation equipment growth capacity are selected to measure the renewable energy consumption potential.

[0023] Furthermore, for example, based on the obtained renewable energy penetration potential indicators and their original data sequence patterns, four prediction models are constructed: Long Short-Term Memory Network (LSTM), Multiple Linear Regression (MLR), Least Squares Support Vector Machine (LSSVM), and Random Forest (RF) models, to predict the renewable energy absorption potential and obtain the prediction results.

[0024] In step S2, for example, based on the results of the four prediction models mentioned above, an MDMSFE combined prediction model covering the four single prediction models is established.

[0025] The expression for the combined prediction model is as follows:

[0026] in, This represents the combined prediction results for period t. These are the weighting coefficients of individual prediction model i in the combined prediction model. This represents the prediction result of a single prediction model i (i = 1, 2, ..., m) in period t, where m is the number of single prediction models, and its value is 4.

[0027] The key to the combined forecasting model is the determination of the weight coefficients. In the DMSFE combined forecasting model, a discount factor β is introduced, and the mean squared error is used to calculate the weight coefficients of each individual model, thereby reducing the mean squared error. The weight coefficients are defined as follows:

[0028] in, t is the actual value at time node t, β is the discount factor with a value range of [0, 1], i′ represents the i′-th time node, and T is the number of observation periods.

[0029] The weighting coefficients are mainly determined by β. In the MDMSFE combined prediction model, β evolves from a single value to a matrix form of β(i,t).

[0030] Furthermore, the objective function and constraints of the quality system are established. Here, the minimum MAPE is used as the objective function to evaluate the predictive performance of the model. The formula for calculating MAPE is as follows:

[0031] in, It is the actual value in period t; This is the predicted value for period t. Weighting coefficients are introduced into the objective function expression to derive the constraints of the objective function. The constraints of the objective function expression include: .

[0032] Next, in step S3, the algorithm program parameters and the quantum-encoded harmonic memory (QHM) are initialized. The main parameters include the number and range of variables, the harmonic memory capacity (HMS), the harmonic memory consideration rate (HMCR), the pitch adjustment rate (PAR), and the algorithm program termination condition (maximum number of iterations).

[0033] In one implementation, when the replacement harmony is improvised, the new solution vector can be generated by three mechanisms: (1) retaining some solution vectors in the quantum-encoded harmony memory (QHM); (2) generating random samples in the quantum-encoded harmony memory (QHM) with the probability of the harmony memory consideration rate (HMCR); and (3) subjecting some components in (1) and (2) to a small perturbation with the probability of the pitch adjustment rate (PAR).

[0034] In one implementation, the best of the two solutions is left in the quantum-encoded and acoustic memory (QHM) by measuring the new quantum harmony and determining whether it is better than the worst harmony in the quantum-encoded and acoustic memory (QHM).

[0035] Furthermore, repeat the above steps until the termination condition is met. When the loop is complete, select the optimal value of β(i,t) of the harmony vector that satisfies the minimum MAPE within the quantum encoding and acoustic memory (QHM), and obtain the optimal solution.

[0036] In step S4, the discount factor matrix β(i,t) is obtained from the above steps, the weighting coefficient ωi of the single prediction model is calculated based on β(i,t), and finally the prediction result value of the QHS-MDMSFE combined prediction model is calculated.

[0037] In summary, the first embodiment of this invention proposes a renewable energy absorption potential prediction method based on a combined model. Addressing the shortcomings of existing renewable energy absorption potential prediction methods, such as insufficient comprehensive consideration of multiple factors, limited applicability of single models, and inconsistent data characteristics across different prediction periods, this method considers multiple key factors, including the maximum generating capacity of renewable energy, actual generating contribution, grid transmission capacity, and the growth potential of renewable energy. It constructs a multi-factor integrated evaluation index system to accurately measure renewable energy absorption potential. Furthermore, it proposes a combined prediction optimization model based on MDMSFE, leveraging the advantages of each model to form a multi-model integrated prediction architecture. This improves the stability and generalization ability of the prediction results, enabling better adaptation to different types of renewable energy and diverse power system scenarios. Finally, it introduces a discount factor β into the MDMSFE combined prediction model, employing different β values ​​for each individual prediction model and each prediction period. This solves the problems of independent information loss in individual prediction models and inconsistent data characteristics across different prediction periods in previous combined prediction models.

[0038] In addition, such as Figure 3 As shown, the second embodiment of the present invention also proposes a renewable energy consumption potential prediction device based on a combined model, which includes, for example, a single model prediction module 201, a combined model establishment module 202, a discount factor optimization module 203, and a joint prediction module 204.

[0039] The single-model prediction module 201 is used to obtain the renewable energy penetration potential index, and performs single-model prediction on the index using a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model, respectively, to generate single-model prediction results. The combined model building module 202 is used to build a combined prediction model based on the single-model prediction results of each model, and constructs constraints with the objective function of minimizing the mean absolute percentage error, and the objective function introduces a discount factor matrix. The discount factor optimization module 203 is used to optimize the discount factor matrix through a quantum-encoded harmony algorithm, iteratively generate new harmonic solutions and update the quantum-encoded harmony memory library until the termination condition is met. The joint prediction module 204 is used to calculate the weight coefficients according to the optimized discount factor matrix and output the joint prediction result of the quantum-encoded harmony memory library and the combined prediction model.

[0040] The renewable energy absorption potential prediction method based on a combined model, implemented by the renewable energy absorption potential prediction device based on a combined model disclosed in the second embodiment of the present invention, is as described in the first embodiment above, and therefore will not be described in detail here. Optionally, each module and the other operations or functions mentioned above are for implementing the method described in the first embodiment, and the beneficial effects of the renewable energy absorption potential prediction device based on a combined model provided in this embodiment are the same as the beneficial effects of the renewable energy absorption potential prediction method based on a combined model provided in the first embodiment above. For the sake of brevity, they will not be repeated here.

[0041] like Figure 4 As shown, the third embodiment of the present invention also proposes an electronic device, for example including: at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit performs the method described in the first embodiment, and the beneficial effects of the electronic device provided in this embodiment are the same as the beneficial effects of the renewable energy consumption potential prediction method based on the combined model provided in the first embodiment.

[0042] like Figure 5 As shown, the fourth embodiment of the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method. The beneficial effects of the computer-readable storage medium provided in this embodiment are the same as those of the renewable energy consumption potential prediction method based on the combined model provided in the first embodiment.

[0043] The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0044] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0045] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0046] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0047] 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; that is, 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 according to actual needs.

[0048] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0049] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0050] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0051] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

[0052] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the renewable energy absorption potential based on a combined model, characterized in that, include: To obtain the renewable energy penetration potential index, single-model predictions were performed on the index using a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model, respectively, generating single-model prediction results. A combined prediction model is established based on the prediction results of each single model, and a constraint condition is constructed with the objective function of minimizing the mean absolute percentage error, and the objective function introduces a discount factor matrix. The discount factor matrix is ​​optimized by quantum-encoded harmony algorithm, new harmonious solutions are iteratively generated and the quantum-encoded harmony memory is updated until the termination condition is met. The weighting coefficients are calculated based on the optimized discount factor matrix, and the joint prediction result of the quantum encoding and acoustic memory and the combined prediction model is output based on the weighting coefficients.

2. The method for predicting renewable energy absorption potential based on a combined model according to claim 1, characterized in that, The expression for the combined prediction model is: ； in, This represents the combined prediction results for period t. These are the weighting coefficients of individual prediction model i in the combined prediction model. This represents the prediction result of a single prediction model i (i = 1, 2, ..., m) in period t, where m is the number of single prediction models, and its value is 4.

3. The renewable energy absorption potential prediction method based on a combined model according to claim 2, characterized in that, The formula for calculating the weighting coefficient is as follows: ； in, t is the actual value at time node t, β is the discount factor with a value range of [0, 1], i′ represents the i′-th time node, and T is the number of observation periods.

4. The renewable energy absorption potential prediction method based on a combined model according to claim 3, characterized in that, The formula for calculating the objective function is as follows: ； in, It is the actual value in period t. It is the predicted value in period t; By introducing the weight coefficients into the expression of the objective function, the constraint expression of the objective function is obtained as follows: 。 5. The method for predicting renewable energy absorption potential based on a combined model according to claim 1, characterized in that, The quantum-encoded harmony algorithm includes: Set the harmony memory library capacity, harmony memory consideration rate, pitch adjustment rate, and maximum number of iterations; Initial harmonious solutions are generated by encoding quantum superposition states; Based on the initial harmonious solution, a new harmonious solution is generated through any of the following mechanisms: retaining the existing solutions in the quantum-encoded harmony memory bank, randomly sampling according to the harmony memory consideration rate probability, or making a small perturbation according to the pitch adjustment rate probability.

6. The renewable energy absorption potential prediction method based on a combined model according to claim 5, characterized in that, The steps for updating the quantum-coded and acoustic memory bank include: The fitness of the new harmonious solution is measured using the objective function as an evaluation index. If the fitness is better than the worst solution in the quantum-encoded and acoustic memory, then the new solution is replaced.

7. The method for predicting renewable energy absorption potential based on a combined model according to claim 1, characterized in that, The optimization of the discount factor matrix includes: The goal is to dynamically weight and minimize the prediction errors of each model at different time periods, so that the data characteristics of the discount factor matrix during the prediction period remain consistent.

8. A device for predicting the renewable energy absorption potential based on a combined model, characterized in that, include: The single-model prediction module is used to obtain the renewable energy penetration potential index. It uses a long short-term memory network model, a multiple linear regression model, a least squares support vector machine model, and a random forest model to perform single-model prediction on the index and generate single-model prediction results. The combined model building module is used to build a combined prediction model based on the prediction results of the single models corresponding to each model, and to construct constraints with the objective function of minimizing the mean absolute percentage error, and the objective function introduces a discount factor matrix; The discount factor optimization module is used to optimize the discount factor matrix through a quantum-encoded harmony algorithm, iteratively generate new harmonic solutions and update the quantum-encoded harmony memory library until the termination condition is met. The joint prediction module is used to calculate weight coefficients based on the optimized discount factor matrix and output the joint prediction results of the quantum-encoded acoustic memory and the combined prediction model.

9. An electronic device, characterized in that, include: A memory and one or more processors connected to the memory, the memory storing a computer program, the processors executing the computer program to implement the renewable energy absorption potential prediction method based on a combined model as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable commands for performing the renewable energy absorption potential prediction method based on a combined model as described in any one of claims 1-7.

Images