A novel power system grid planning method for high proportion of new energy

Abstract

The application discloses a novel power system grid planning method for high-proportion new energy, and relates to the technical field of power system planning.The method comprises the following specific steps: multi-source data acquisition: through the establishment of an adaptive interface with a high-precision meteorological satellite data receiving system, meteorological satellite data containing conventional and micro-meteorological level influence new energy output fluctuation data are acquired; the application can accurately master the influence on new energy power generation efficiency and the attitude tendency information of the public to the new energy grid planning project by collecting and fusing meteorological satellite data, geographic information system data and social media big data; meanwhile, combined with the ecological environment influence evaluation step, the influence of grid facilities and new energy power station construction on the ecological system and the environmental benefits brought by new energy utilization are quantitatively analyzed, so that the actual characteristics and ecological environment factors of new energy can be fully considered in the grid planning, and the scientificity and rationality of the grid planning are improved.

Description

Technical Field

[0001] This invention relates to the field of power system planning technology, specifically to a novel power grid planning method for power systems with a high proportion of new energy sources. Background Technology

[0002] In the medical environment, video surveillance systems play a crucial role. They not only help ensure the safety of medical facilities but also assist in the management of medical affairs and, to some extent, support medical services. With the continuous advancement of medical technology and the rapid growth of medical data, the demand for video surveillance systems is also increasing, especially in the area of ​​healthcare big data privacy management, where video surveillance systems need to provide more efficient and intelligent monitoring solutions.

[0003] Traditional power grid planning methods have revealed numerous shortcomings when facing the challenge of high-proportion renewable energy integration in new power systems. These methods primarily rely on limited basic data such as power load and generation capacity, as well as traditional factors like power transmission efficiency and cost. They lack a comprehensive understanding and accurate prediction of the characteristics of renewable energy output. Furthermore, traditional power grid planning methods neglect the important role of ecological and environmental factors in power grid planning, making it difficult for planning schemes to simultaneously ensure power supply and take into account ecological protection and sustainable development. In addition, traditional methods have limitations in processing multi-source data, failing to fully utilize the rich information provided by diverse data sources such as meteorological satellites, geographic information systems, and social media, thus limiting the scientific rigor and accuracy of planning schemes. Therefore, traditional power grid planning methods are no longer sufficient to meet the needs of efficient and sustainable development in new power systems.

[0004] To address the aforementioned issues, it is necessary to optimize existing power grid planning methods for high-proportion renewable energy sources. This involves collecting and analyzing multi-source data to construct a comprehensive model, fully assessing the output characteristics and ecological impact of renewable energy sources, and then building a comprehensive evaluation index system. Intelligent optimization algorithms can then be used for power grid planning. Therefore, developing a new power grid planning method for high-proportion renewable energy sources that can comprehensively achieve these characteristics is of great significance. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a novel power grid planning method for power systems with a high proportion of renewable energy. This method constructs a comprehensive and accurate data foundation by collecting and integrating multi-source data, including meteorological satellite data, geographic information system (GIS) data, and social media big data. Based on this foundation, a comprehensive model is built to accurately predict the output characteristics of renewable energy and optimize the power grid layout. Furthermore, this method fully considers ecological and environmental factors, using an ecological and environmental assessment model to evaluate the environmental impact of the power grid planning scheme and quantify environmental benefits, ensuring the scientific nature and sustainability of the planning scheme. In addition, by employing intelligent optimization algorithms and geographic information system (GIS) visualization technology, this method achieves intelligent and refined power grid planning, improving planning efficiency and accuracy.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a novel power grid planning method for power systems oriented towards high proportions of new energy sources, the method comprising the following specific steps:

[0007] Multi-source data acquisition: Meteorological satellite data, including both conventional and micro-meteorological data affecting the fluctuation of new energy output, is acquired by establishing an interface with a high-precision meteorological satellite data receiving system and stored in a cache. At the same time, it is stably connected to a geographic information database to extract the topography and geomorphology around the new energy power plant and related data that affect the efficiency of new energy collection. This data is then categorized, stored, and indexed. In addition, web crawlers and social media platform interfaces are used to collect humanistic and social data on public attitudes toward the construction of new energy facilities based on a set scope and keywords. This data is preprocessed and stored to provide a multi-source data foundation for subsequent analysis.

[0008] Multi-source data fusion and comprehensive model construction: Data cleaning methods are used to remove data that does not meet the requirements, and standardized methods are used to unify the data format. By building a model architecture that combines deep learning and machine learning, key feature vectors are extracted from multi-source heterogeneous data, the correlation between data and its impact on the output characteristics of new energy are explored, and a comprehensive model that can reflect the actual environmental output characteristics and development environment of new energy is constructed based on the extracted feature vectors. The model parameters are updated based on newly collected data.

[0009] Ecological and environmental impact assessment: Using professional ecological and environmental assessment models, the relevant geographical information and scale parameters of power grid facilities and new energy power plant construction layout are used as inputs to analyze the aspects of animal and plant habitats, water resource conservation and soil quality in the ecosystem. The impact of construction activities on the ecosystem is comprehensively assessed and a report is generated. At the same time, a calculation model is constructed based on energy-related theories and national standards to quantify the reduction of air pollutants brought about by the replacement of traditional energy with new energy.

[0010] Construction of a comprehensive evaluation index system: Collect index data on ecological and environmental benefits, power grid supply benefits, construction and operation and maintenance costs, and the stability of new energy output; sort out the interrelationships and importance weights among the indicators; construct a hierarchical structure model using the analytic hierarchy process; determine the relative importance weights of each indicator and conduct consistency checks; combine the fuzzy comprehensive evaluation method to perform fuzzy quantification on fuzzy indicators; and generate a spatial layout evaluation index system through multiple calculations to measure the merits of different power grid planning schemes.

[0011] Intelligent optimization planning: By incorporating geospatial location information into the geographic weighted regression algorithm, the local impact of geographic factors on power grid planning elements is analyzed. Combined with spatial autocorrelation analysis, the correlation and clustering characteristics between elements are explored. Based on geographic information data and analysis results, candidate areas for power grid line routes, substation sites and new energy power plant distribution that meet the conditions of ecological suitability and reasonable construction cost are selected. Then, using intelligent optimization algorithms, with the comprehensive evaluation index system as the objective function, the planning elements are set as optimization variables and constraints are defined. Multiple rounds of search and iterative optimization calculations are carried out in the candidate areas to find the optimal power grid planning scheme.

[0012] Results Output and Visualization: Extract, organize and output the relevant data of the optimal power grid planning scheme determined by intelligent optimization planning. Use geographic information system visualization technology to display the power grid line route, substation and new energy power station distribution information on the electronic map. The power grid layout is clearly presented through visualization. At the same time, a detailed report containing various planning indicators and parameters is generated.

[0013] Furthermore, in the multi-source data fusion and comprehensive model construction step, a model architecture combining deep learning and machine learning is built to extract key feature vectors from multi-source heterogeneous data. The algorithm formula is as follows: ,in, Indicates at time The input is preprocessed multi-source heterogeneous data. It is the weight matrix of the convolutional layer in a convolutional neural network, used to extract spatial features from the data. It is the corresponding bias term. This indicates that the convolutional neural network at time t... Output feature representation, It is the weight matrix of a recurrent neural network. It is its bias term. It is the recurrent neural network at the previous time step. The hidden state, At any moment The hidden states of the recurrent neural network, which combine the output features of the CNN, are used as the extracted comprehensive feature vectors for subsequent comprehensive model generation steps to explore the deep correlation features of multi-source data and their impact on the output characteristics of new energy sources.

[0014] Furthermore, in the multi-source data fusion and integrated model construction step, an integrated model that reflects the actual environmental output characteristics and development environment of new energy is constructed using the extracted feature vectors. The calculation formula is as follows: ,in, Indicated in grid cell Inland habitat for species The quality score It is a species Habitat suitability score, It is a grid cell The degree of habitat degradation, It is the half-saturation constant. It is a dimensionless shape parameter. By substituting relevant parameters from different regions into this formula, the habitat quality score of different species within each grid cell can be calculated. This allows for a quantitative analysis of the impact of power grid and new energy power plant construction on the quality of plant and animal habitats, resulting in an ecosystem impact assessment report.

[0015] Furthermore, in the aforementioned ecological and environmental impact assessment step, a professional ecological and environmental assessment model is used to comprehensively assess the impact of construction activities on the ecosystem and generate a report. The model formula is as follows: ,in, Indicators representing the comprehensive impact of the ecological environment This is the overall adjustment coefficient. These correspond to three ecosystem levels: plant and animal habitats, water resource conservation, and soil quality. This represents the different evaluation units subdivided at each ecological level. It is the first The first ecological level The weighting coefficients of each evaluation unit, Indicates the first The first ecological level The changes in ecological function indicators of each evaluation unit before and after the construction and layout of power grid facilities and new energy power plants. It is the first The first ecological level The initial values ​​of ecological function indicators for each evaluation unit before construction and layout. It is the first The first ecological level The construction impact sensitivity coefficient of each evaluation unit. This indicates the different factors that influence the degree of environmental impact of construction activities. It is the first The first ecological level Within the evaluation unit, the first The quantitative value of each influencing factor.

[0016] Furthermore, in the aforementioned ecological and environmental impact assessment step, a calculation model is constructed based on energy-related theories and national standards to quantify the reduction in air pollutant emissions brought about by the replacement of traditional energy sources with new energy sources. The calculation formula is as follows: ,in, Indicates targeting specific pollutants The emission reduction Representing different time periods. Indicates the total number of time periods. Indicates different energy types, It is the total number of energy types involved. Indicates the time period Internal energy Energy efficiency Refers to the time period Internal energy Actual usage and They are traditional energy and new energy Emission factors, It is targeted at specific pollutants In time period Internal characteristic adjustment coefficient.

[0017] Furthermore, in the step of constructing the comprehensive evaluation index system, the analytic hierarchy process (AHP) is used to construct a hierarchical structure model, determine the relative importance weights of each index, and perform a consistency check. The algorithm model is as follows: ,in, This is the relative weight vector of the desired indicators. It is an approximate eigenvector obtained by calculating the eigenvector method. This is the number of indicators at that level; this formula is used to... Normalization is performed to obtain a weight vector that meets the requirements. Combining the fuzzy comprehensive evaluation method, for some indicators with fuzziness and uncertainty, fuzzy quantification is performed using membership functions to transform qualitative indicators into quantitative indicators that can participate in the comprehensive evaluation calculation, and then the calculation is performed according to the first-level fuzzy comprehensive evaluation formula: ,in, It is the vector of the first-level fuzzy comprehensive evaluation results. It is the weight vector of each indicator. It is a fuzzy relation matrix, symbol " "" indicates fuzzy synthesis operation, thereby realizing a comprehensive evaluation of power grid planning schemes that takes fuzziness into account, and generating a spatial layout evaluation index system.

[0018] Furthermore, in the intelligent optimization planning step, a geographic weighted regression algorithm is used to incorporate geospatial location information to analyze the local impact of geographic factors on power grid planning elements. The calculation formula is as follows: ,in, In terms of geographical location Observed values ​​of power grid planning elements at the location Geographical location Geographic coordinates In position The intercept term, In position The first One independent variable The regression coefficients, yes The independent variables that influence power grid planning elements This is the error term, representing the position. The random error component that the model cannot explain.

[0019] Furthermore, in the intelligent optimization planning step, an intelligent optimization algorithm is used, with a comprehensive evaluation index system as the objective function, planning elements as optimization variables and clear constraints, to conduct multiple rounds of search and iterative optimization calculations within the candidate region to find the optimal power grid planning scheme. The calculation formula is as follows: Among them, Fitness is the individual's fitness value. , , , These are respectively assigned ecological and environmental benefits. Power supply reliability Construction and operation costs Stability of new energy power output The weight coefficients are used to guide the genetic algorithm through the fitness function to search for the power grid planning scheme with the best comprehensive benefits within the candidate region, thereby achieving the goal of intelligent optimization planning.

[0020] An electronic device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the novel power system grid planning method for high-proportion renewable energy described above.

[0021] A computer-readable storage medium includes a stored computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the novel power system grid planning method for high-proportion renewable energy sources described above.

[0022] Compared with existing technologies, this novel power system grid planning method for high-proportion renewable energy sources has the following advantages:

[0023] I. This invention, by collecting and integrating meteorological satellite data, geographic information system data, and social media big data, can accurately grasp the impact on the efficiency of new energy power generation and the public's attitude towards new energy power grid planning projects. At the same time, combined with the ecological and environmental impact assessment steps, it quantitatively analyzes the impact of power grid facilities and new energy power plant construction on the ecosystem, as well as the environmental benefits brought by the utilization of new energy. This enables power grid planning to fully consider the actual characteristics of new energy and ecological and environmental factors, thereby improving the scientificity and rationality of power grid planning and ensuring that the power grid can efficiently accommodate new energy while minimizing the impact on the ecological environment.

[0024] Second, this invention employs an intelligent optimization algorithm with a comprehensive evaluation index system as the objective function to optimize planning elements such as power grid route alignment, substation site selection, and distribution of new energy power plants. By setting corresponding constraints and conducting multiple rounds of deep search and iterative optimization calculations within the geographical space, the optimal power grid planning scheme is found. This not only improves the efficiency of power grid planning but also ensures that the planning scheme guarantees the reliability of power supply, efficiently accommodates new energy sources, and minimizes the negative impact on the ecological environment. This is of great significance for promoting the sustainable development of new power systems.

[0025] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating the operation of a new power grid planning method for a high proportion of new energy sources in a new type of power system.

[0028] Figure 2 This is a flowchart of a new power system grid planning method oriented towards a high proportion of new energy sources. Detailed Implementation

[0029] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0030] A mountainous area plans to vigorously develop new energy power and build a new power system, expecting to connect a high proportion of wind power and photovoltaic new energy to meet the growing local electricity demand and reduce dependence on traditional fossil energy. The mountainous area has complex terrain, including many high mountains, valleys and rivers, with rich and diverse ecological environment, habitats of many rare animals and plants, and multiple villages and other residential areas, which have high requirements for ecological protection and power supply reliability.

[0031] By collaborating with professional meteorological data service providers, a receiving channel was established to acquire high-precision meteorological satellite data. Data updates were scheduled to be received hourly. In addition to standard average wind speed and light intensity data, the focus was on micro-meteorological data, such as local airflow changes in valleys and the impact of rapid cloud movement on sunshine duration. This data was stored on a local meteorological data server, categorized and archived by date and time for easy retrieval and analysis. High-precision GIS data of the mountainous area was also obtained from the local surveying and mapping department. Geographic information software was used to extract detailed topographic information within a 30-kilometer radius of the planned new energy power plant area, distinguishing different terrain types such as ridges, valleys, steep slopes, gentle slopes, and water bodies. The impact of each terrain type on the solar and wind energy collection efficiency of wind and solar power plants was analyzed. For example, steep slopes are unfavorable for the installation of solar panels and stable sunlight, while valleys may experience increased wind speeds. The rapid effect is beneficial to wind power generation, etc. Data related to topography and new energy collection efficiency are structured and stored according to geographic coordinates and terrain categories to build a spatial database for rapid querying and spatial analysis. Simultaneously, web crawling technology is used to target content posted by users in the mountainous area and surrounding regions on local social media platforms (such as local forums and social media groups) and mainstream social media platforms. Information containing keywords such as "wind power construction," "photovoltaic power station," and "power supply" is filtered to collect public attitudes towards new energy infrastructure construction, concerns (such as worries about ecological damage, landscape impact, and noise pollution), and desired improvements in power supply. The collected data is processed and analyzed weekly, and after removing duplicate and irrelevant information, it is stored in a dedicated text database. Natural language processing technology is used to extract key viewpoints and sentiments to prepare for subsequent understanding of public opinion and consideration of social impact factors.

[0032] Using the Python programming language and relevant data processing libraries, a data cleaning program was written to remove outliers from meteorological satellite data (such as wind speeds exceeding extreme values ​​that are impossible under local geographical and climatic conditions), erroneous coordinate information from GIS data, and irrelevant text content from social media big data that is clearly not relevant to the topic. The Min-Max normalization method was used to standardize all numerical data (such as quantitative data such as wind speed, light intensity, and terrain slope) and map them uniformly to the [0, 1] interval to ensure that data from different sources and of different magnitudes can be fused and analyzed on the same scale.

[0033] A feature extraction model architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) based on deep learning is constructed. Preprocessed multi-source heterogeneous data is organized into the model according to time series and spatial location. The CNN part is used to extract the spatial correlation features between topography and meteorological data (e.g., extracting the impact features on wind power output from the spatial relationship between topography and local airflow changes). The RNN part captures the temporal changes of these features and the temporal correlations between different data (e.g., the dynamic impact of changes in sunlight intensity with time and meteorological conditions on photovoltaic output). The algorithm formula is as follows: ,in, Indicates at time The input is preprocessed multi-source heterogeneous data. It is the weight matrix of the convolutional layer in a convolutional neural network, used to extract spatial features from the data. It is the corresponding bias term. This indicates that the convolutional neural network at time t... Output feature representation, It is the weight matrix of a recurrent neural network. It is its bias term. It is the recurrent neural network at the previous time step. The hidden state, At any moment By combining the output features of CNN with the hidden states of the recurrent neural network, and through multiple training and adjustment of model parameters, a set of key feature vectors is finally extracted. These feature vectors cover the comprehensive impact of various factors such as terrain, meteorology, and human factors on the output characteristics of new energy.

[0034] Using the extracted feature vector set as the independent variable and the actual power output of the new energy power station as the dependent variable, a multiple linear regression model is constructed. The model is trained based on historical observation data (power output data from previously operating small-scale new energy demonstration projects and corresponding multi-source environmental data), fitting regression coefficients and intercept terms to obtain a comprehensive model reflecting the power output characteristics of new energy in the mountainous area under complex actual conditions. The calculation formula is as follows: ,in, Indicated in grid cell Inland habitat for species The quality score It is a species Habitat suitability score, It is a grid cell The degree of habitat degradation, It is the half-saturation constant. It is a dimensionless shape parameter. By substituting relevant parameters from different regions into this formula, the habitat quality score of different species within each grid cell can be calculated. This allows for the quantitative analysis of the impact of power grid and new energy power plant construction on the quality of plant and animal habitats, generating an ecosystem impact assessment report. Simultaneously, new data is collected regularly to update and validate the model, ensuring that it can accurately adapt to the impact of environmental changes and the expansion of new energy project scale, so that it can always provide a reliable basis for predicting new energy output for subsequent planning.

[0035] The ecological environment assessment model is imported, and geographic information data such as the planned power grid route (several candidate lines initially proposed), substation site selection (several candidate sites in valleys and plains), and new energy power plant layout (locations of wind power and photovoltaic power plants planned in different terrain areas) are input into the model, along with parameters such as the expected construction scale and land area of ​​each facility. Combined with basic ecological data such as land use type and vegetation coverage extracted from GIS data, the model is used to analyze the impact of different construction schemes on various aspects of the local ecosystem, including animal and plant habitats (e.g., the degree of fragmentation of habitats of certain rare birds, changes in the activity range of mammals), water resource conservation (e.g., the impact on surface water and groundwater recharge of mountain streams and small reservoirs), and soil quality (e.g., the increased risk of soil erosion caused by construction). A detailed ecosystem impact assessment report is generated, and the changes in ecological indicators in different areas are displayed in the form of visual maps and data tables, clearly identifying ecologically sensitive areas and areas significantly affected by construction, providing an intuitive basis for subsequent layout optimization.

[0036] Based on the carbon emission coefficients and air pollutant emission factor standards for various energy sources published by the national energy authorities, and combined with the current usage of traditional energy (mainly small diesel generators used to power some remote villages) and the projected power generation of new energy in the mountainous area, calculations were performed according to the algorithm formula for quantifying the carbon emission reduction and air pollutant emission reduction brought about by the replacement of traditional energy with new energy. For example, the amount of diesel generators that are expected to be replaced by wind power and photovoltaic new energy power generation each year was calculated in detail, and the corresponding environmental benefit indicators such as carbon dioxide emission reduction and sulfur dioxide emission reduction were obtained. These data were compiled into charts to intuitively present the potential contribution of new energy projects in improving regional environmental quality, so as to be comprehensively considered with other planning factors.

[0037] Comprehensive data collection was conducted on ecological and environmental benefit indicators obtained from the ecological and environmental impact assessment process (such as habitat quality change scores and emission reductions of different pollutants), traditional power supply benefit indicators of the power grid (including the System Average Outage Frequency Index (SAIFI) and System Average Outage Duration Index (SAIDI) derived from statistical analysis of local historical power supply data, as well as power supply capacity indicators estimated according to power grid planning and design standards, such as the maximum power supply load of each substation), and construction and operation and maintenance cost data (estimated through communication with engineering construction departments and equipment suppliers, including power grid line construction costs, substation construction and operation and maintenance costs, and new energy power plant construction and operation and maintenance costs under different terrain conditions in mountainous areas). The seminar, which included detailed items such as the output stability index of new energy sources (output volatility, intermittent characteristic index, etc. calculated from the time series data of new energy output power) and the analysis of the multi-source data fusion and comprehensive model construction steps, organized a seminar with power system experts, ecological environment experts and representatives of relevant local government departments to jointly sort out the interrelationships between the various indicators, analyze the synergistic effects of different indicators in reflecting the overall situation of the mountain power grid planning (such as a good ecological environment helps to ensure the stable output of new energy sources, thereby improving power supply efficiency) and the restrictive relationships (such as improving power supply reliability may increase construction costs), and clarify the importance and weight of each indicator for the overall evaluation.

[0038] A hierarchical model was constructed using the Analytic Hierarchy Process (AHP). This model includes a target layer (comprehensive evaluation target for mountainous renewable energy power grid planning), a criterion layer (divided into four main criteria: ecological and environmental benefits, power supply benefits, cost, and renewable energy output stability), and a scheme layer (different candidate power grid planning schemes, with several combinations of different line routes, site selections, and renewable energy layouts set based on preliminary planning). Questionnaires were distributed to experts to collect their scores, gathering their opinions on the relative importance of each indicator in pairwise comparisons. A judgment matrix was constructed, and mathematical calculations were used to determine the relative importance weights of each indicator relative to the higher-level indicators. A rigorous consistency check was performed to ensure the rationality of the weight allocation. The algorithm model is as follows: ,in, This is the relative weight vector of the desired indicators. It is an approximate eigenvector obtained by calculating the eigenvector method. This is the number of indicators at that level; this formula is used to... Normalization is performed to obtain a weight vector that meets the requirements. By combining the fuzzy comprehensive evaluation method (FCE), and targeting the fuzzy indicator of public attitudes toward the construction of new energy facilities, the membership function is used to perform fuzzy quantification based on different inclinations of public opinion (such as strong support, support, neutral, opposition, and strong opposition), transforming it into a quantitative indicator that can participate in the comprehensive evaluation calculation. After multiple hierarchical analysis and fuzzy comprehensive evaluation calculations, a unified and comprehensive spatial layout evaluation index system suitable for the characteristics of the mountainous area is finally generated to accurately measure the advantages and disadvantages of different power grid planning schemes in many aspects.

[0039] The Geographically Weighted Regression (GWR) algorithm was employed. Geographic coordinates (longitude and latitude), topographic relief, distance from settlements, and land use type—data collected from various locations in the mountainous area—were used as independent variables. Planning elements such as power grid construction costs, power supply distance, and power loss were used as dependent variables to construct a GWR model. Spatial analysis tools in Geographic Information System (GIS) software were used, combined with actually collected data, to perform model calculations and analyze the local impact of various geographic spatial factors on planning elements at different geographical locations. The calculation formula is as follows: ,in, In terms of geographical location Observed values ​​of power grid planning elements at the location Geographical location Geographic coordinates In position The intercept term, In position The first One independent variable The regression coefficients, yes The independent variables that influence power grid planning elements This is the error term, representing the position. The model addresses random errors that cannot be explained by other factors. For example, it was found that construction costs for power lines are significantly increased in mountainous areas due to complex terrain and distance from residential areas, while valley areas with flat terrain and close proximity to existing roads have obvious advantages in power supply distance. Furthermore, the model explores the correlations and clustering characteristics among geospatial power grid planning elements, revealing a certain clustering pattern between the distribution of new energy power plants and substation locations. Specifically, these plants tend to be concentrated in ecologically suitable areas close to load centers. Based on these spatial analysis results, and combined with established screening criteria such as ecological suitability (avoiding habitats of rare plants and animals, protecting water conservation areas, etc.) and construction cost rationality (controlling line construction costs within budget, reducing operation and maintenance costs, etc.), the spatial query and analysis functions of GIS are used to select candidate areas for power grid line routes, substation locations, and new energy power plant distribution that meet the requirements. This forms a candidate area dataset, which is then visualized on a GIS platform for easy and intuitive viewing and further analysis.

[0040] Intelligent optimization is performed using intelligent optimization algorithms. With a comprehensive evaluation index system as the objective function, planning elements such as the coordinates of each node of the power grid lines within the candidate area, the capacity of substations, and the installed capacity and distribution coordinates of new energy power plants are set as optimization variables. Corresponding constraints are also clearly defined, such as prohibiting construction within ecological protection red lines, maintaining a safe electrical distance between power lines and high-voltage transmission lines, and ensuring that substation sites meet flood control requirements. The calculation formula is as follows: Among them, Fitness is the individual's fitness value. , , , These are respectively assigned ecological and environmental benefits. Power supply reliability Construction and operation costs Stability of new energy power output The weight coefficients are used to guide the genetic algorithm through the fitness function to search for the power grid planning scheme with the best comprehensive benefits within the candidate region, thereby achieving the goal of intelligent optimization planning.

[0041] The data information related to the optimal power grid planning scheme determined by the intelligent optimization planning steps is extracted and organized. This includes the coordinate sequence of the final determined power grid line routes (recording the start, end, and turning points of each line in latitude and longitude coordinates), the geographical location information of each substation site (precise geographical coordinates and corresponding altitude information), and the coordinates and installed capacity of the distribution of new energy power stations (the central coordinates of each power station and the expected wind power and photovoltaic installed capacity). Using visualization technology, this information is displayed on an electronic map, with different colored lines representing power grid lines of different voltage levels and different shapes and colors of icons distinguishing between substations and new energy power stations. Simultaneously, based on the ecological and environmental impact assessment... The results include special marking of ecologically sensitive areas (e.g., using green shading to represent ecological protection zones), visually presenting the spatial relationship between the entire power grid layout and the ecological environment. In addition, reports containing detailed information such as the length of each power grid line, the capacity of each substation, the expected environmental benefits (e.g., annual carbon emission reduction, pollutant emission reduction), and estimated construction and operation costs are generated. The specific values ​​of each indicator and related explanations are presented in tabular form, making it easy for planners, decision-makers, local departments, and residents to clearly and intuitively view and understand the planning results. This provides strong guidance for the specific implementation of the new power system in the mountainous area, ensuring that the project construction can proceed smoothly and meet the dual goals of ecological protection and power supply needs.

[0042] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A novel power grid planning method for power systems oriented towards high proportions of new energy sources, characterized in that, The method includes the following specific steps: Multi-source data acquisition: Meteorological satellite data, including both conventional and micro-meteorological data affecting the fluctuation of new energy output, is acquired by establishing an interface with a high-precision meteorological satellite data receiving system and stored in a cache. At the same time, it is stably connected to a geographic information database to extract the topography and geomorphology around the new energy power plant and related data that affect the efficiency of new energy collection. This data is then categorized, stored, and indexed. In addition, web crawlers and social media platform interfaces are used to collect humanistic and social data on public attitudes toward the construction of new energy facilities based on a set scope and keywords. This data is preprocessed and stored to provide a multi-source data foundation for subsequent analysis. Multi-source data fusion and comprehensive model construction: Data cleaning methods are used to remove data that does not meet the requirements, and standardized methods are used to unify the data format. By building a model architecture that combines deep learning and machine learning, key feature vectors are extracted from multi-source heterogeneous data, the correlation between data and its impact on the output characteristics of new energy are explored, and a comprehensive model that can reflect the actual environmental output characteristics and development environment of new energy is constructed based on the extracted feature vectors. The model parameters are updated based on newly collected data. Ecological and environmental impact assessment: Using professional ecological and environmental assessment models, the relevant geographical information and scale parameters of power grid facilities and new energy power plant construction layout are used as inputs to analyze the aspects of animal and plant habitats, water resource conservation and soil quality in the ecosystem. The impact of construction activities on the ecosystem is comprehensively assessed and a report is generated. At the same time, a calculation model is constructed based on energy-related theories and national standards to quantify the reduction of air pollutants brought about by the replacement of traditional energy with new energy. Construction of a comprehensive evaluation index system: Collect index data on ecological and environmental benefits, power grid supply benefits, construction and operation and maintenance costs, and the stability of new energy output; sort out the interrelationships and importance weights among the indicators; construct a hierarchical structure model using the analytic hierarchy process; determine the relative importance weights of each indicator and conduct consistency checks; combine the fuzzy comprehensive evaluation method to perform fuzzy quantification on fuzzy indicators; and generate a spatial layout evaluation index system through multiple calculations to measure the merits of different power grid planning schemes. Intelligent optimization planning: By incorporating geospatial location information into the geographic weighted regression algorithm, the local impact of geographic factors on power grid planning elements is analyzed. Combined with spatial autocorrelation analysis, the correlation and clustering characteristics between elements are explored. Based on geographic information data and analysis results, candidate areas for power grid line routes, substation sites and new energy power plant distribution that meet the conditions of ecological suitability and reasonable construction cost are selected. Then, using intelligent optimization algorithms, with the comprehensive evaluation index system as the objective function, the planning elements are set as optimization variables and constraints are defined. Multiple rounds of search and iterative optimization calculations are carried out in the candidate areas to find the optimal power grid planning scheme. Results Output and Visualization: Extract, organize and output the relevant data of the optimal power grid planning scheme determined by intelligent optimization planning. Use geographic information system visualization technology to display the power grid line route, substation and new energy power station distribution information on the electronic map. The power grid layout is clearly presented through visualization. At the same time, a detailed report containing various planning indicators and parameters is generated.

2. The novel power system grid planning method for high-proportion renewable energy sources according to claim 1, characterized in that, In the multi-source data fusion and comprehensive model construction step, a model architecture combining deep learning and machine learning is built to extract key feature vectors from multi-source heterogeneous data. The algorithm formula is as follows: ,in, Indicates at time The input is preprocessed multi-source heterogeneous data. It is the weight matrix of the convolutional layer in a convolutional neural network, used to extract spatial features from the data. It is the corresponding bias term. This indicates that the convolutional neural network at time t... Output feature representation, It is the weight matrix of a recurrent neural network. It is its bias term. It is the recurrent neural network at the previous time step. The hidden state, At any moment The hidden states of the recurrent neural network, which combine the output features of the CNN, are used as the extracted comprehensive feature vectors for subsequent comprehensive model generation steps to explore the deep correlation features of multi-source data and their impact on the output characteristics of new energy sources.

3. The novel power system grid planning method for high-proportion renewable energy sources according to claim 1, characterized in that, In the multi-source data fusion and integrated model construction step, an integrated model that reflects the actual environmental output characteristics and development environment of new energy is constructed using the extracted feature vectors. The calculation formula is as follows: ,in, Indicated in grid cell Inland habitat for species The quality score It is a species Habitat suitability score, It is a grid cell The degree of habitat degradation, It is the half-saturation constant. It is a dimensionless shape parameter. By substituting relevant parameters from different regions into this formula, the habitat quality score of different species within each grid cell can be calculated. This allows for a quantitative analysis of the impact of power grid and new energy power plant construction on the quality of plant and animal habitats, resulting in an ecosystem impact assessment report.

4. The novel power system grid planning method for high-proportion renewable energy sources according to claim 1, characterized in that, In the aforementioned ecological and environmental impact assessment step, a professional ecological and environmental assessment model is used to comprehensively assess the impact of construction activities on the ecosystem and generate a report. The model formula is as follows: ,in, Indicators representing the comprehensive impact of the ecological environment This is the overall adjustment coefficient. These correspond to three ecosystem levels: plant and animal habitats, water resource conservation, and soil quality. This represents the different evaluation units subdivided at each ecological level. It is the first The first ecological level The weighting coefficients of each evaluation unit, Indicates the first The first ecological level The changes in ecological function indicators of each evaluation unit before and after the construction and layout of power grid facilities and new energy power plants. It is the first The first ecological level The initial values ​​of ecological function indicators for each evaluation unit before construction and layout. It is the first The first ecological level The construction impact sensitivity coefficient of each evaluation unit. This indicates the different factors that influence the degree of environmental impact of construction activities. It is the first The first ecological level Within the evaluation unit, the first The quantitative value of each influencing factor.

5. A novel power grid planning method for a high proportion of new energy sources in a power system according to claim 1, characterized in that, In the aforementioned ecological and environmental impact assessment step, a calculation model is constructed based on energy-related theories and national standards to quantify the reduction in air pollutant emissions brought about by the replacement of traditional energy with new energy sources. The calculation formula is as follows: ,in, Indicates targeting specific pollutants The emission reduction Representing different time periods. Indicates the total number of time periods. Indicates different energy types, It is the total number of energy types involved. Indicates the time period Internal energy Energy efficiency Refers to the time period Internal energy Actual usage and They are traditional energy and new energy Emission factors, It is targeted at specific pollutants In time period Internal characteristic adjustment coefficient.

6. A novel power grid planning method for a high proportion of new energy sources in a power system according to claim 1, characterized in that, In the steps of constructing the comprehensive evaluation index system, the analytic hierarchy process (AHP) is used to build a hierarchical structure model, determine the relative importance weights of each index, and perform a consistency check. The algorithm model is as follows: ,in, This is the relative weight vector of the desired indicators. It is an approximate eigenvector obtained by calculating the eigenvector method. This is the number of indicators at that level; this formula is used to... Normalization is performed to obtain a weight vector that meets the requirements. Combining the fuzzy comprehensive evaluation method, for some indicators with fuzziness and uncertainty, fuzzy quantification is performed using membership functions to transform qualitative indicators into quantitative indicators that can participate in the comprehensive evaluation calculation, and then the calculation is performed according to the first-level fuzzy comprehensive evaluation formula: ,in, It is the vector of the first-level fuzzy comprehensive evaluation results. It is the weight vector of each indicator. It is a fuzzy relation matrix, symbol " "" indicates fuzzy synthesis operation, thereby realizing a comprehensive evaluation of power grid planning schemes that takes fuzziness into account, and generating a spatial layout evaluation index system.

7. A novel power grid planning method for a high proportion of new energy sources in a power system according to claim 1, characterized in that, In the intelligent optimization planning step, a geographic weighted regression algorithm is used to incorporate geospatial location information to analyze the local impact of geographic factors on power grid planning elements. The calculation formula is as follows: ,in, In terms of geographical location Observed values ​​of power grid planning elements at the location Geographical location Geographic coordinates In position The intercept term, In position The first One independent variable The regression coefficients, yes The independent variables that influence power grid planning elements This is the error term, representing the position. The random error component that the model cannot explain.

8. A novel power grid planning method for a high proportion of new energy sources in a power system according to claim 1, characterized in that, In the intelligent optimization planning step, an intelligent optimization algorithm is used, with a comprehensive evaluation index system as the objective function, planning elements as optimization variables and clear constraints. Multiple rounds of search and iterative optimization calculations are conducted within the candidate region to find the optimal power grid planning scheme. The calculation formula is as follows: Among them, Fitness is the individual's fitness value. , , , These are respectively assigned ecological and environmental benefits. Power supply reliability Construction and operation costs Stability of new energy power output The weight coefficients are used to guide the genetic algorithm through the fitness function to search for the power grid planning scheme with the best comprehensive benefits within the candidate region, thereby achieving the goal of intelligent optimization planning.

9. An electronic device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the novel power system grid planning method for high-proportion renewable energy sources as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the novel power system grid planning method for high-proportion new energy sources as described in any one of claims 1 to 8.

Images