New energy base multi-objective optimization planning method based on GIS data processing and elastic load curve modeling

Abstract

The invention provides a new energy base multi-objective optimization planning method based on GIS data processing and elastic load curve modeling, and the method comprises the steps: obtaining a GIS data set and rasterized data of a research region, and obtaining a historical load data set, electric equipment characteristics and a historical power parameter set of a receiving end region; constructing an elastic load curve according to the historical load data set, the electric equipment characteristics, the new energy equipment parameters and the historical electric power parameters; obtaining a constructable area according to the GIS data set, the transmission and distribution channel division and the rasterized data; and according to the elastic load curve and the constructable area, constructing an optimization model with optimization objectives including minimization of total investment cost, minimization of ecological influence and maximization of power supply reliability to obtain an optimal planning scheme, and planning a new energy base in the research area. According to the method, damage to the ecological environment can be effectively avoided, the construction difficulty and risk are reduced, and the obtained planning scheme achieves optimal balance in the aspects of economy, ecology, power supply and the like.

Description

Technical Field

[0001] This invention relates to the field of new energy base planning technology, specifically to a multi-objective optimization planning method for new energy bases based on GIS data processing and elastic load curve modeling. Background Technology

[0002] With the core objective of building a new power system and a collaborative system for ecological governance, the desert region has been positioned as the main battleground for new energy development. In the planning of large-scale power bases in the desert region, existing technical solutions mainly focus on single-factor considerations. For example, Chinese patent application CN119106756A, "A Method for Planning and Parameter Optimization of Power Generation, Grid, Storage, and DC Power Generation in Desert Region New Energy Bases," primarily uses the collection of local load data and power transmission data of the planned desert energy base to establish an optimization model for wind and solar power station capacity configuration and layout, aiming to achieve optimal configuration and layout. However, planning schemes based on this optimization method have shortcomings in spatial layout rationality, potentially causing damage to the ecological environment and increasing construction difficulty and risks. Furthermore, in actual operation, new energy bases struggle to effectively match load demand, failing to fully leverage the power supply advantages of new energy and reducing power supply reliability and economy. Moreover, this optimization method cannot achieve an optimal balance in the planning scheme, failing to meet the complex needs of new energy base planning in the desert region. Summary of the Invention

[0003] This invention addresses the problems existing in the prior art by providing a multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling. This method enables a more rational spatial layout of new energy bases, better adapts to load fluctuations, and improves the reliability and economy of power supply. It can effectively avoid damage to the ecological environment, reduce construction difficulty and risks, and achieve an optimal balance in terms of economy, ecology and power supply.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: a multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling, comprising: acquiring parameters of the study area, transmission and distribution channels, receiving end areas, and new energy equipment; GIS datasets and raster data were obtained based on the research area. Based on the receiving-end region, historical load datasets, electrical equipment characteristics, and historical power parameter sets are obtained; A flexible load curve is constructed based on the historical load dataset, the characteristics of the electrical equipment, the parameters of the new energy equipment, and the historical power parameters. The constructable area is obtained based on the GIS dataset, the distribution channel delineation, and the raster data; An optimization model is constructed based on the elastic load curve and the buildable area; the optimization objectives of the optimization model include minimizing total investment cost, minimizing ecological impact, and maximizing power supply reliability. The optimal planning scheme is obtained based on the optimization model. Based on the optimal planning scheme, a new energy base is planned within the study area.

[0005] In some embodiments, constructing a flexible load curve based on the historical load dataset, the characteristics of the electrical equipment, the parameters of the new energy equipment, and the historical power parameters includes: The historical load dataset is preprocessed to obtain a time series dataset; The data variation patterns of the time series dataset were obtained; A baseline load curve is obtained based on the time series dataset and the data variation patterns. A first value range is obtained based on the historical power parameter set and the time series dataset; The power parameter response threshold is obtained based on the characteristics of the electrical equipment and the data change pattern. The power parameter response coefficient is obtained based on the first value range; Demand-side response adjustment is constructed based on the characteristics of the electrical equipment, the data change pattern, the power parameter response coefficient, and the power parameter response threshold. A flexible load curve model is constructed based on the baseline load curve, the demand-side response adjustment, and the parameters of the new energy equipment. The elastic load curve is obtained by using a machine learning algorithm based on the time series dataset, the data change pattern, and the elastic load curve model.

[0006] In some embodiments, the data change patterns include load growth trends, load fluctuation characteristics, and load regulation capabilities.

[0007] In some embodiments, the load growth trend is a long-term load growth trend.

[0008] In some embodiments, the load fluctuation characteristics include daily load fluctuation characteristics, weekly load fluctuation characteristics, and monthly load fluctuation characteristics.

[0009] In some embodiments, the elastic load curve model is constructed using a piecewise linear model.

[0010] In some embodiments, the rasterized data includes at least two raster cells; Based on the GIS dataset, the distribution channel delineation, and the raster data, the constructable areas include: The prohibited construction zones are obtained based on the GIS dataset; The area to be planned is obtained based on the rasterized data and the prohibited construction zone; Based on the GIS dataset, the resource score and ecological sensitivity score of each grid cell in the area to be planned are obtained respectively; The distance score of each grid cell in the area to be planned is obtained based on the distribution channel; Based on preset weights, the suitability score of each grid cell in the area to be planned is obtained according to the resource score, the ecological sensitivity score, and the distance score. The buildable area is obtained based on the suitability score.

[0011] In some embodiments, the step of obtaining the optimal planning scheme based on the optimization model includes: Step S1: Obtain at least one intermediate planning scheme based on the optimization model; Step S2: Use time-series production simulation to verify the intermediate planning scheme corresponding to the highest suitability score and obtain the verification results; When the verification result meets the optimization objective, step S3 is executed; If the verification result does not meet the optimization objective, adjust the optimization model according to the verification result and repeat steps S1 and S2. Step S3: Obtain the optimal planning scheme based on the intermediate planning scheme corresponding to the highest suitability score.

[0012] In some embodiments, adjusting the optimization model includes adjusting the power parameter response coefficient, the power parameter response threshold, and the preset weights.

[0013] In some embodiments, the prohibited construction zone includes ecological protection zones and topographic factor zones.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The multi-objective optimization planning method for new energy bases based on GIS data processing and elastic load curve modeling provided by this invention can fully consider spatial factors such as topography and ecological protection zones in desert areas through refined GIS data processing, making the spatial layout of new energy bases more reasonable, effectively avoiding damage to the ecological environment, reducing construction difficulty and risk, and improving the feasibility and reliability of planning schemes. 2. This invention fully considers the demand-side response capability and future load change trends through elastic load curve modeling, enabling the planned new energy base to better adapt to load fluctuations, improve the reliability and economy of power supply, and enhance the performance of the new energy base in actual operation.

[0015] 3. This invention, through a multi-objective optimization model, comprehensively considers multiple objectives such as total investment cost, ecological impact, and power supply reliability. The resulting planning scheme achieves an optimal balance in terms of economy, ecology, and power supply. Compared with existing methods, it has better comprehensive benefits and competitiveness, providing strong technical support for the sustainable development of new energy bases in desert and Gobi areas. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling in an embodiment of the present invention. Figure 2 This is a schematic diagram of the elastic load curve construction process in an embodiment of the present invention; Figure 3 This is a schematic diagram of the process of obtaining the optimal planning scheme based on the optimization model in an embodiment of the present invention. Detailed Implementation

[0017] In existing technologies, the spatial data processing in new energy base planning is not refined enough. GIS technology is not fully utilized for in-depth mining and analysis of spatial data related to the complex topography and ecological protection zones in desert areas, resulting in deficiencies in the spatial layout rationality of planning schemes. This may cause potential damage to the ecological environment and increase the difficulty and risk of construction. Regarding load modeling, demand-side response capabilities and future load dynamics are not considered, and a flexible load curve modeling step is lacking. This makes it difficult for planned new energy bases to effectively match load demand in actual operation, failing to fully leverage the power supply advantages of new energy sources and reducing power supply reliability and economy. In terms of optimization solutions, existing technologies rarely consider multiple objectives simultaneously, such as total investment cost, ecological impact, and power supply reliability, and do not employ effective hierarchical optimization algorithms to coordinate and optimize these objectives. Therefore, existing planning methods are unlikely to achieve an optimal balance between economy, ecology, and power supply, failing to meet the complex needs of new energy base planning in desert areas.

[0018] To clearly illustrate the technical features of this solution, the implementation methods of this application will be described in detail below with reference to the accompanying drawings and embodiments. This will allow for a full understanding and implementation of how this application uses technical means to solve technical problems and achieve corresponding technical effects. The embodiments of this application and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this application.

[0019] See Figure 1This invention provides a multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling, including: acquiring the study area, transmission and distribution channels, receiving end areas, and new energy equipment parameters; GIS datasets and raster data were obtained based on the study area; GIS datasets obtained based on the study area include: Data on topography, elevation, ecological protection zone boundaries, and distribution of scenic resources in the study area, namely the desert region, were collected and imported into a GIS database. By performing coordinate unification processing on the data in the GIS database to obtain the GIS dataset, and using a unified coordinate system, the consistency and accuracy of the data in the GIS dataset can be ensured. Obtaining rasterized data based on the study area includes: dividing the study area into raster of a preset size to obtain rasterized data, which is used to prepare for subsequent spatial analysis, thereby obtaining an accurate buildable area; Historical load datasets, electrical equipment characteristics, and historical power parameter sets are obtained based on the receiving end region. The historical load dataset contains historical load curve data, which includes electricity consumption data and power data for different time periods. Different time periods include hours, days, and months. The time span for obtaining historical load curve data covers at least the past 3 to 5 years to fully reflect the long-term trend and seasonal patterns of load data, and to extract typical daily load curves and typical seasonal load curves.

[0020] The historical power parameter set is the set of power parameter values ​​that change over time, corresponding to the time span of the data in the historical load dataset. A flexible load curve is constructed based on historical load datasets, characteristics of electrical equipment, parameters of new energy equipment, and historical power parameters. The buildable area is obtained based on GIS datasets, distribution channel delineation, and raster data; An optimization model is constructed based on the flexible load curve and the buildable area; the optimization objectives of the optimization model include minimizing total investment cost, minimizing ecological impact, and maximizing power supply reliability. The optimal planning scheme is obtained based on the optimization model; preferably, the optimization model is solved by a hierarchical optimization algorithm. The hierarchical optimization algorithm can weigh multiple objectives to obtain the optimal new energy base planning scheme, balancing key factors such as economic efficiency, ecological impact and power supply reliability. New energy bases are planned within the study area based on the optimal planning scheme.

[0021] Beneficially, the multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling provided by this invention, through refined GIS data processing, can fully consider spatial factors such as topography and ecological protection zones in desert and Gobi areas, making the spatial layout of new energy bases more rational, effectively avoiding damage to the ecological environment, reducing construction difficulty and risks, and improving the feasibility and reliability of the planning scheme. Flexible load curve modeling fully considers demand-side response capabilities and future load change trends, enabling the planned new energy bases to better adapt to load fluctuations, improving power supply reliability and economy, and enhancing the performance of new energy bases in actual operation. Through the multi-objective optimization model, comprehensively considering multiple objectives such as total investment cost, ecological impact, and power supply reliability, the resulting planning scheme achieves an optimal balance in terms of economy, ecology, and power supply, exhibiting better comprehensive benefits and competitiveness compared to existing methods, and providing strong technical support for the sustainable development of new energy bases in desert and Gobi areas.

[0022] See Figure 2 In some embodiments, constructing a resilient load curve based on historical load datasets, electrical equipment characteristics, renewable energy equipment parameters, and historical power parameters includes: Preprocessing the historical load dataset yields a time series dataset, including: The first intermediate dataset is obtained by removing outliers and erroneous records from the historical load dataset, such as outliers and erroneous records caused by data missing or measurement errors. The data in the first intermediate dataset is preprocessed using methods such as data interpolation and data smoothing to obtain the second intermediate dataset, thereby improving the accuracy and completeness of the data. The data in the second intermediate dataset are organized in chronological order to form a continuous time series dataset, which facilitates subsequent analysis and modeling. Obtain patterns of data change from time series datasets; In some embodiments, data change patterns include load growth trends, load fluctuation characteristics, and load regulation capabilities; Load growth trend refers to determining the long-term growth trend of load by analyzing load data in a time-series dataset. Time-series analysis methods, including moving averages and exponential smoothing, are used to fit and predict load data in the time-series dataset to obtain the long-term load growth curve. Based on factors such as economic growth and population growth, the load growth in the receiving-end region over the next 5-10 years is predicted, providing a basis for generating a resilient load curve. In some embodiments, the load growth trend represents the long-term load growth trend.

[0023] Load fluctuation characteristics study the fluctuation of load over different time periods. In some embodiments, load fluctuation characteristics include daily, weekly, and monthly load fluctuation characteristics. The degree of load fluctuation can be quantified based on time-series datasets by calculating statistical indicators such as the standard deviation and variance of the load. Furthermore, load fluctuation characteristics also include the periodicity and regularity of load fluctuations, such as the load difference between weekdays and weekends and load changes during holidays, providing a basis for constructing flexible load curves.

[0024] Load regulation capacity refers to the analysis of the changing trend of load regulation capacity based on changes in the regulating power source. Changes in the regulating power source include the transformation of coal-fired power plants to be more flexible and the application of new energy storage technologies. Studying load regulation capacity helps to more accurately predict the adjustable range and capacity of future loads.

[0025] Parameters such as adjustable load ratio and response latency are obtained from time series datasets; A baseline load curve is obtained based on the time series dataset and data change patterns. The baseline load curve can be predicted based on the time series dataset and load growth trend. The first range of values ​​is obtained based on historical power parameter sets and time series datasets; Power parameter response thresholds are obtained based on the characteristics of electrical equipment and data variation patterns. ; The power parameter response coefficient is obtained based on the first value range. Power parameter response coefficient The user's response sensitivity coefficient to electricity prices reflects the degree to which users are sensitive to changes in electricity prices; Based on the characteristics of electrical equipment, data change patterns, and power parameter response coefficients and power parameter response threshold Construct demand-side response adjustment measures; A flexible load curve model is constructed based on the baseline load curve, demand-side response adjustment, and parameters of new energy equipment. In some embodiments, a piecewise linear model is used to construct the flexible load curve model. Compared with the nonlinear model, the piecewise linear model has a better balance between computational complexity and fitting accuracy, and is more suitable for the application scenarios of this invention. By extracting curves from time series datasets, obtaining parameters such as demand-side response adjustment amounts, and determining relevant parameters for the elastic load curve model, we can accurately generate elastic load curves that are realistic and take into account future changes, providing key basis for the planning of new energy bases. The elastic load curve model is as follows: ; ; ; In the formula, For time; This is an elastic load curve; This is the baseline load curve; Adjustable capabilities for the user side.

[0026] Load changes driven by economic factors such as electricity prices; for The power parameter value at any given time is the real-time electricity price; This is the power parameter response threshold, representing the critical value at which users begin to respond to changes in electricity prices; The power parameter response coefficient is the user's sensitivity coefficient to electricity prices, representing the load adjustment caused by a unit change in electricity price.

[0027] For energy storage regulation; It contributes to distributed resources, including various distributed loads. The schedulable coefficient for distributed resources; Contribute to V2G; This refers to adjustable power output, including demand-side response load and regulating power supply. It is an adjustable power factor. The charging power for energy storage, The discharge power of the stored energy. For the charging period of energy storage, This is the discharge period for energy storage. For user response rate, For V2G efficiency. The power of the electric vehicle; Machine learning algorithms are used to obtain elastic load curves based on time series datasets, data change patterns, and elastic load curve models. The impact of load growth trends, load fluctuation characteristics, and increased load forecasting difficulty on elastic load curves is comprehensively considered. For example, the slope and amplitude of the baseline load curve are adjusted when the load increases, the impact of new load access on load fluctuation characteristics is considered, and advanced forecasting methods such as machine learning and deep learning methods are used to improve forecasting accuracy.

[0028] In some of these embodiments, the rasterized data includes at least two raster cells; Based on the GIS dataset, distribution corridor delineation, and raster data, the buildable areas include: Based on the GIS dataset, prohibited construction zones are obtained. In some embodiments, the prohibited construction zones include ecological protection zones and topographic factor zones. The prohibited construction zones include a first prohibited construction zone and a second prohibited construction zone: Based on the ecological protection zone boundary data in the GIS dataset, the raster cells within the ecological protection zone boundary in the rasterized data are set as the first prohibited construction zone to protect the ecological environment; considering topographic factors, the raster cells corresponding to areas with slopes greater than a preset value are set as the second prohibited construction zone to avoid building new energy bases in rugged areas and reduce construction difficulty and risk. The area to be planned is obtained from the rasterized data and the prohibited construction zone; the area to be planned is obtained by removing the prohibited construction zone from the rasterized data, that is, after removing the raster cells corresponding to the prohibited construction zone from the rasterized data, the remaining raster cells are the area to be planned. Based on the GIS dataset, the resource score and ecological sensitivity score of each raster cell in the area to be planned are obtained. The resource score is used to reflect the abundance of new energy resources such as wind and solar power in the raster cell, while the ecological sensitivity score is used to reflect the ecological sensitivity of the raster cell. The lower the ecological sensitivity, the higher the ecological sensitivity score. The distance score of each grid cell in the area to be planned is obtained based on the transmission and distribution channel. The distance score is calculated based on the distance between the grid cell and the transmission and distribution channel. The distance score is used to reflect the distance between the grid cell and the transmission and distribution channel, i.e. the power grid. The closer the distance, the higher the distance score. Based on preset weights, a suitability score is obtained for each grid cell within the planning area according to resource score, ecological sensitivity score, and distance score; the formula for the suitability score is: in, For the first Suitability score for each grid cell, For grid cell number, For the first Resource score for each grid cell. Assign weights to resource scores; For the first Ecological sensitivity score of each grid cell, As a weight for ecological sensitivity scoring; For the first Distance score for each grid cell, This is the weight for distance scoring.

[0029] Based on the suitability score, buildable areas are obtained. A preset score threshold is set, and grid cells with a suitability score not less than the score threshold are selected to enter the optimization pool. The grid cells in the optimization pool are buildable areas.

[0030] Protecting spatial constraint modeling technology based on GIS datasets, including the rules for setting prohibited construction zones and the calculation methods and formulas for suitability scores, can scientifically select areas suitable for building new energy bases, taking into account factors such as ecological environmental protection, construction difficulty and risks, and resources, thereby improving the rationality and feasibility of new energy base planning.

[0031] See Figure 3 In some embodiments, the step of obtaining the optimal planning scheme based on the optimization model includes: Step S1: Obtain at least one intermediate planning scheme based on the optimization model; Step S2: Use time-series production simulation to verify the intermediate planning schemes corresponding to the suitability scores and obtain the verification results; When the verification results meet the construction requirements, proceed to step S3; the verification results meeting the construction requirements must include at least a curtailment rate that meets the construction requirements, typically not exceeding 5%, and in some areas not exceeding 10%; When the verification results do not meet the construction requirements, the optimization model is adjusted based on the verification results, and steps S1 and S2 are repeated. In some embodiments, adjusting the optimization model includes adjusting the power parameter response coefficient based on a first value range and adjusting the power parameter response threshold. And adjust the preset weights; Step S3: Obtain the optimal planning scheme based on the intermediate planning schemes corresponding to the suitability score.

[0032] By adjusting parameters such as the power parameter response coefficient and load regulation time constant in the flexible load curve model, as well as the preset weights in the suitability score, the verification and optimization model of the scheme can be iterated. The complete mechanism of verification and iteration can ensure the feasibility and effectiveness of the final planning scheme, continuously optimize the scheme until it meets the requirements, and ensure the smooth implementation and long-term stable operation of the new energy base construction.

[0033] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, and is not intended to limit the scope of protection of the present invention. Simple modifications or equivalent substitutions made by those skilled in the art to the technical solution of the present invention do not depart from the essence and scope of the technical solution of the present invention.

Claims

1. A multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling, characterized in that, include: Acquire parameters of the research area, transmission and distribution channels, receiving end areas, and new energy equipment; GIS datasets and raster data were obtained based on the research area. Based on the receiving-end region, historical load datasets, electrical equipment characteristics, and historical power parameter sets are obtained; A flexible load curve is constructed based on the historical load dataset, the characteristics of the electrical equipment, the parameters of the new energy equipment, and the historical power parameters. The constructable area is obtained based on the GIS dataset, the distribution channel delineation, and the raster data; An optimization model is constructed based on the elastic load curve and the buildable area; the optimization objectives of the optimization model include minimizing total investment cost, minimizing ecological impact, and maximizing power supply reliability. The optimal planning scheme is obtained based on the optimization model. Based on the optimal planning scheme, a new energy base is planned within the study area.

2. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 1, characterized in that, Constructing a flexible load curve based on the historical load dataset, the characteristics of the electrical equipment, the parameters of the new energy equipment, and the historical power parameters includes: The historical load dataset is preprocessed to obtain a time series dataset; The data variation patterns of the time series dataset were obtained; A baseline load curve is obtained based on the time series dataset and the data variation patterns. A first value range is obtained based on the historical power parameter set and the time series dataset; The power parameter response threshold is obtained based on the characteristics of the electrical equipment and the data change pattern. The power parameter response coefficient is obtained based on the first value range; Demand-side response adjustment is constructed based on the characteristics of the electrical equipment, the data change pattern, the power parameter response coefficient, and the power parameter response threshold. A flexible load curve model is constructed based on the baseline load curve, the demand-side response adjustment, and the parameters of the new energy equipment. The elastic load curve is obtained by using a machine learning algorithm based on the time series dataset, the data change pattern, and the elastic load curve model.

3. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 2, is characterized in that... The data change patterns include load growth trends, load fluctuation characteristics, and load regulation capabilities.

4. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 3, is characterized in that... The load growth trend mentioned is the long-term growth trend of the load.

5. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 3, is characterized in that... The load fluctuation characteristics include daily load fluctuation characteristics, weekly load fluctuation characteristics, and monthly load fluctuation characteristics.

6. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 3, is characterized in that... The elastic load curve model is constructed using a piecewise linear model.

7. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 2, characterized in that, The rasterized data includes at least two raster cells; Based on the GIS dataset, the distribution channel delineation, and the raster data, the constructable areas include: The prohibited construction zones are obtained based on the GIS dataset; The area to be planned is obtained based on the rasterized data and the prohibited construction zone; Based on the GIS dataset, the resource score and ecological sensitivity score of each grid cell in the area to be planned are obtained respectively; The distance score of each grid cell in the area to be planned is obtained based on the distribution channel; Based on preset weights, the suitability score of each grid cell in the area to be planned is obtained according to the resource score, the ecological sensitivity score, and the distance score. The buildable area is obtained based on the suitability score.

8. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 7, is characterized in that... The steps to obtain the optimal planning scheme based on the optimization model include: Step S1: Obtain at least one intermediate planning scheme based on the optimization model; Step S2: Use time-series production simulation to verify the intermediate planning scheme corresponding to the highest suitability score and obtain the verification results; When the verification results meet the construction requirements, proceed to step S3; If the verification results do not meet the construction requirements, adjust the optimization model according to the verification results and repeat steps S1 and S2. Step S3: Obtain the optimal planning scheme based on the intermediate planning scheme corresponding to the highest suitability score.

9. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 8, characterized in that, Adjusting the optimization model includes adjusting the power parameter response coefficient, the power parameter response threshold, and the preset weights.

10. The multi-objective optimization planning method for new energy bases based on GIS data processing and flexible load curve modeling as described in claim 7, characterized in that, The prohibited construction areas include ecological protection zones and areas affected by topographic factors.

Images