Urban agglomeration expansion-oriented photovoltaic power station site selection optimization method

Abstract

The invention belongs to the technical field of artificial intelligence in renewable energy application, and particularly relates to an urban agglomeration expansion-oriented photovoltaic power station site selection optimization method. The method comprises the following specific steps: S1, acquiring data and preprocessing the data; s2, constructing an interactive linear model and predicting an address with solar radiation potential; s3, constructing a ConvLSTM network, and predicting potential photovoltaic sites and the photovoltaic installed capacity of each site; s4, the city expansion degree is quantified, and a photovoltaic site site with small influence on environment and economic development is selected according to the city expansion trend and the prediction development direction; s5, carrying out comprehensive evaluation by adopting a CRITIC-TOPSIS method, and determining an optimal construction site; the method can effectively evaluate the adaptability of the photovoltaic power generation potential and space resources and landforms, also considers and balances the land utilization efficiency, environmental protection requirements and economic benefits, and provides an important reference basis for the site selection of a photovoltaic power station in an urbanized region.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence in renewable energy applications, and specifically relates to a photovoltaic power station site selection optimization method for urban agglomeration expansion. Background Art

[0002] As global energy demand continues to rise and traditional energy systems pose severe challenges to the ecological environment, the development and efficient use of renewable energy has become a core strategy for global energy transformation and sustainable development. Among them, solar photovoltaic power generation technology has become the focus of widespread attention from the international community due to its huge resource reserves and clean and pollution-free characteristics. However, with the rapid expansion of photovoltaic power station installed capacity, the scarcity of land resources has become increasingly prominent, which has directly led to rising construction costs for photovoltaic power stations and challenges to economic benefits.

[0003] In view of this, the scientific planning and reasonable layout of photovoltaic power stations have become the key links to ensure the success of the project. In the early stage of project implementation, site selection plays a vital role. Improper site selection will directly lead to a significant decrease in power generation and an increase in maintenance expenses, thereby weakening the economic feasibility and environmental friendliness of the project, and may even have an adverse impact on the surrounding ecosystem. Therefore, the site selection process of photovoltaic power stations requires the comprehensive use of multidisciplinary knowledge and technical means such as geographic information technology, meteorological data analysis, and environmental impact assessment, aiming to identify high-quality areas that can maximize the use of solar energy resources and effectively balance land use, environmental protection and economic benefits, laying a solid foundation for the sustainable development of photovoltaic power stations.

[0004] When evaluating the potential of photovoltaic power generation, existing photovoltaic power station site selection strategies mainly focus on the meteorological parameters of the planned area, especially the analysis of historical light intensity and surface temperature data, and use this as a basis to predict the photovoltaic power generation capacity of the area. Although some methods have recognized the importance of matching photovoltaic space resources with topographic features and have tried to take them into consideration, when faced with specific areas where urbanization is accelerating, these strategies generally ignore the profound impact of dynamic changes in economic factors and environmental protection needs on site selection decisions.

[0005] Therefore, it is of great significance to develop a photovoltaic power plant site selection optimization method for urban agglomeration expansion. Summary of the invention

[0006] Purpose of the invention: The technical problem to be solved by the present invention is to provide an integrated geographic information and meteorological data, and innovatively propose a photovoltaic power station site selection optimization method for urban agglomeration expansion. This method can not only effectively evaluate the adaptability of photovoltaic power generation potential and spatial resources and topography, but also consider the balance between land use efficiency, environmental protection needs and economic benefits, and provide an important reference for the site selection of photovoltaic power stations in urbanized areas.

[0007] In order to solve the above technical problems, the present invention discloses a photovoltaic power station site selection optimization method for urban agglomeration expansion, and the specific steps are as follows:

[0008] S1. Acquire data and preprocess the data;

[0009] S2. Construct interactive linear models and select sites with solar radiation potential;

[0010] S3. Construct a ConvLSTM network and predict potential PV sites and the PV installed capacity of each site;

[0011] S4. Quantify the extent of urban expansion and select photovoltaic site locations with minimal impact on the environment and economic development based on urban expansion trends and predicted development directions;

[0012] S5. Use the CRITIC-TOPSIS method to conduct a comprehensive evaluation and determine the best construction site.

[0013] Among them, in S1, the data includes terrain data, meteorological data, power grid coverage and transportation network data, photovoltaic sites and photovoltaic installed capacity data in different research areas in different years, and remote sensing data; the preprocessing operations include data cleaning, data deduplication, data deletion, removal of anomalies and noise points, and replacement of anomalies with mean values.

[0014] Preferably, terrain data: obtain digital elevation models (DEM) and land use type data of the study area in different years, such as DEM data and CLCD data of the Yangtze River Delta region from 2010 to 2022, and use GIS to calculate geographic information data of the study area, including slope, aspect, altitude, etc.;

[0015] Meteorological data: Collect meteorological data of the study area, including temperature, humidity, precipitation, cloud cover, air pressure, solar radiation, etc., and use the simple averaging method to obtain meteorological data with a time resolution of 1 hour. For example, use the ERA5 reanalysis dataset to obtain meteorological data of the Yangtze River Delta region for each month from 2010 to 2022, and unify them into a time resolution of 1 day;

[0016] Grid coverage and transportation network data: Obtain grid distribution data to determine the distribution of grids and major transportation roads and railways in the study area.

[0017] Remote sensing data: Use the Google Earth Engine (GEE) platform to collect remote sensing image data of the study area at different times, such as collecting Landsat series data in the Yangtze River Delta region from 2010 to 2022 on a monthly basis. Calculate the land surface temperature (LST) and remote sensing normalized indicators NDVI, NDBI, NDWI, and NDBal in the study area. LST is calculated using a single-channel algorithm, and the calculation formula is as follows:

[0018] L λ =M L +DN+A L

[0019]

[0020] T LST =T-273.15

[0021] Where L λ is the radiation brightness, DN represents the digital value of the thermal infrared band, M L and A L are the correction parameters, which can be found in the metadata file, T is the surface temperature (unit: K), c1 and c2 are Planck constants, which are 1.1910429e -5 [W·m 2 / (sr·μm 4 ) and 1.4387753 [m·μm], λ is the central wavelength of the band (unit: μm), which can be obtained from the metadata file, T LST is the surface temperature (unit: °C).

[0022] The calculation formulas for remote sensing normalized indicators NDVI, NDBI, NDWI and NDBal are as follows:

[0023]

[0024] Among them, nir represents the near infrared band, red represents the infrared band, swir1 represents the shortwave infrared 1 band, and thermal represents the thermal infrared band.

[0025] The specific steps of S2 are:

[0026] S21. Interaction and analysis of variables;

[0027] S22. Construct interactive linear model;

[0028] S23. Validate the model;

[0029] S24. Select a site with solar radiation potential.

[0030] Preferably, in S21, the variable interaction and analysis is specifically to select variables with strong pairwise correlation to constitute variable interaction pairs. The variable correlation matrix is ​​constructed using the Pearson correlation analysis method, and the variables with strong pairwise correlation are analyzed to constitute possible interaction pairs. Geodetector geographic detectors are established: factor detector (Factor Detector) and interaction detector (Interaction Detector). The factor detector is used to evaluate the explanatory power of each single standard's contribution to solar radiation, which is achieved by calculating the q statistic. The interaction detector is used to explore the potential interaction effects between different standards, and the interaction q statistic of the two standards is calculated and compared with the q statistic of the individual standard to determine whether their interaction relationship is enhanced or weakened. The calculation of the q statistic is as follows:

[0031]

[0032] Where q is a criterion that represents the explanatory power of the response variable Y. In this study, Y refers to the solar radiation DSR; h represents the number of categories of the response variable Y or factor X; N h and N represent the total number of units in the hth class and the total number of units in the entire region, respectively; and σ 2 The q statistic ranges from 0 to 1. The larger the q value, the stronger the explanatory power of factor X for Y, and vice versa.

[0033] Preferably, in S22, the linear interaction model is constructed as follows:

[0034] The forward stepwise regression method was used to gradually add each single factor and pairwise interaction factor into the model, estimate the specific impact of each single factor and pairwise interaction variable on the response variable (solar radiation), and select the one with the highest accuracy (R 2 The model with the highest value is taken as the final interactive linear model. Based on the results of forward stepwise regression, a basic linear model and an interactive linear model are established, and the prediction accuracy of the two is compared. The formulas of the established basic linear model and interactive linear model are as follows:

[0035]

[0036] Among them, y is the response variable, which refers to solar radiation DSR in this study; x i is the i-th factor, β i is the coefficient to be estimated corresponding to each single factor i; x j x k Represents x j and x k The interaction betweenjk is the estimated coefficient corresponding to each pair of interaction variables; β0 describes the intercept on the y-axis; u is a random error term.

[0037] Preferably, in S23, the specific steps of model verification are: randomly selecting 1000 points for testing, and calculating Cronbach's α coefficient for model verification. The calculation formula of Cronbach's α coefficient is as follows:

[0038]

[0039] Where k represents the number of items that need to be compared; is the square of the standard deviation of each individual measurement (i.e., the variance), is the square of the population standard deviation.

[0040] Preferably, in S24, the specific steps of selecting an address with solar radiation potential are:

[0041] The study area is divided into several surface grid units, and the established interactive linear model is used to predict the solar radiation data of each studied surface grid unit, and the overall solar radiation distribution map of the study area is drawn. Locations with high solar radiation potential and other suitable conditions are screened out, and these locations are further evaluated to confirm whether they meet the actual construction conditions, such as the convenience of connecting to the power grid and traffic traversal type, and the grid units that meet the conditions are used as alternative grid units.

[0042] The specific steps of S3 are:

[0043] S31. Construct ConvLSTM network;

[0044] S32. Train the ConvLSTM model using historical data, and use the cross-validation method to evaluate the performance of the model and adjust the model parameters;

[0045] S33. Use the model trained in S32 to predict photovoltaic sites.

[0046] The specific steps of S4 are: collecting remote sensing data of the study area and using GEE to calculate the surface temperature, analyzing the four indicator data of NDVI, NDBI, NDWI, and NDBal, and combining the historical data of urban agglomeration expansion to quantify the degree of urban expansion; analyzing the trend of urban expansion in the study grid, and quantifying the degree of urban expansion in each study grid area, calculating the expansion area, expansion rate and expansion intensity, analyzing the trend of urban expansion in the study grid, and predicting possible future development directions; combining the regional economic development plan, evaluating the impact of the construction of photovoltaic sites on the environment, avoiding negative impacts on the local ecosystem, and at the same time, according to the surface cover type data of each candidate grid unit and the expansion trend of the urban agglomeration, selecting the grid unit area with small impact on the environment and economic development from the available photovoltaic site selection sites;

[0047] Preferably, the calculation formulas for the expansion rate and expansion strength are as follows:

[0048]

[0049] In the formula, ΔU ij is the urban expansion area of ​​the i-th research unit during period j; Δt ij is the time span of period j; ULA ij is the urban area of ​​the ith research unit at the beginning of period j; TLA ij is the total land area of ​​the ith research unit. The urban area in this study is expressed by the urban construction land area.

[0050] The specific steps of S5 are: using the CRITIC-TOPSIS method to comprehensively evaluate the addresses with solar radiation potential obtained in S2, the potential photovoltaic sites and the photovoltaic installed capacity of each site obtained in S3, and the photovoltaic site selection sites with little impact on the environment and economic development obtained in S4, so as to determine the best location for the construction of the solar power station.

[0051] Preferably, the specific steps of the CRITIC-TOPSIS method evaluation are:

[0052] S51. Data standardization: For positive indicators, the standardization formula is:

[0053]

[0054] For negative indicators, the standardized formula is:

[0055]

[0056] Where: x ij is the value of the jth indicator in the ith alternative, r ij is the standardized value;

[0057] S52.CRITIC weight calculation:

[0058] First, calculate the standard deviation σ of each indicator j :

[0059]

[0060] in is the mean of the jth indicator, and m is the number of alternatives;

[0061] Then calculate the correlation coefficient matrix R between the indicators jk :

[0062]

[0063] Among them, r ik represents the standardized value of the i-th alternative on the k-th indicator, It represents the mean value of the kth indicator, which is obtained by averaging the standardized values ​​of all alternatives on this indicator. Its calculation formula is as follows:

[0064]

[0065] Next, calculate the weight w of each indicator j :

[0066]

[0067] S53. Construct a weighted decision matrix:

[0068] The element v of the weighted decision matrix ij The calculation formula is:

[0069] v ij =r ij × j

[0070] S54. Calculate the distance between the ideal solution and the negative ideal solution:

[0071] Ideal solution A + and negative ideal solution A - They are:

[0072] A + ={max(v ij )|j=1,2,...,n}

[0073] A - ={min(v ij )|j=1,2,...,n}

[0074] Calculate the distance of each solution to the ideal solution and the negative ideal solution respectively:

[0075]

[0076] S55. Calculate relative proximity:

[0077] Relative proximity The calculation formula is:

[0078]

[0079] S56. Sorting:

[0080] Based on relative proximity Sort the options, the larger the value, the higher the priority, and determine the final optimal construction location.

[0081] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the photovoltaic power station site selection optimization method for urban agglomeration expansion of the present invention.

[0082] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the photovoltaic power station site selection optimization method for urban agglomeration expansion of the present invention are implemented.

[0083] Beneficial effects: 1. The present invention adopts a photovoltaic power station site selection optimization method for urban agglomeration expansion, which can effectively integrate and extract useful information from multi-source data such as remote sensing image data, meteorological data, ground observation data, photovoltaic site spatial distribution and photovoltaic installed capacity data.

[0084] 2. The present invention introduces the conv-LSTM model and constructs a model that can automatically learn complex features in the data and realize spatiotemporal prediction of photovoltaic sites. At the same time, after parameter optimization, the model can effectively and accurately perform spatiotemporal prediction of photovoltaic sites and installed capacity prediction of each site.

[0085] 3. The present invention introduces an interactive linear model to minimize the impact of subjective decision-making. By introducing interaction terms between factors, it can better capture the mutual influence between factors, thereby improving the accuracy and reliability of site selection for solar photovoltaic power stations.

[0086] 4. While considering the impact of natural factors on the site selection of photovoltaic power stations, the present invention also considers the impact of urban agglomeration development on the site selection of photovoltaic power stations. By quantifying the degree of expansion of urban agglomerations and simultaneously selecting the CRITIS-TOPSIS method, each influencing indicator is objectively scored, which can reduce the subjectivity and uncertainty of indicator selection to a certain extent, thereby enabling a comprehensive evaluation of the construction site of the photovoltaic site and ultimately determining the optimal construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0088] Figure 1 This is a flow chart of a photovoltaic power station site selection optimization method for urban agglomeration expansion in an embodiment of the present invention. DETAILED DESCRIPTION

[0089] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0090] Embodiment 1:

[0091] like Figure 1 As shown, this embodiment provides a photovoltaic power station site selection optimization method for urban agglomeration expansion, and takes the Yangtze River Delta region as an example. The detailed steps are as follows:

[0092] Step 1: Data acquisition and preprocessing

[0093] Collect all the data in the study area and perform data preprocessing operations, including data cleaning, data deduplication, data deletion, removal of anomalies and noise points, and replacing anomalies with mean values. The specific types of data collected are:

[0094] 1. Collection of variable data such as topography, weather, power grid and traffic distance:

[0095] Topographic data: Obtain digital elevation models (DEM) and land use type data of the study area in different years, such as DEM data and CLCD data of the Yangtze River Delta region from 2010 to 2022, and use GIS to calculate geographic information data of the study area, including slope, aspect, altitude, etc.;

[0096] Meteorological data: Collect meteorological data of the study area, including temperature, humidity, precipitation, cloud cover, air pressure, solar radiation, etc., and use the simple averaging method to obtain meteorological data with a time resolution of 1 hour. For example, the meteorological data of the Yangtze River Delta region in each month from 2010 to 2022 are obtained by using the ERA5 reanalysis dataset and unified into a time resolution of 1 day. The formula of the simple averaging method is as follows:

[0097]

[0098] where x1,x2,...x n It represents the meteorological data of the 1st hour, 2nd hour, and up to the nth hour in the meteorological data with a time resolution of 1 hour. n is 24, which means the meteorological data of the 24th hour and 0:00 in the morning. Indicates the meteorological data obtained with a time resolution of 1 day;

[0099] Grid coverage and transportation network data: Obtain grid distribution data to determine the distribution of grids and major transportation roads and railways in the study area.

[0100] 2. Acquisition of PV site and PV installed capacity data in different research areas and years:

[0101] The spatial distribution data of photovoltaic sites in the Yangtze River Delta region and the installed capacity data of each photovoltaic site from 2010 to 2022 are collected and visualized with images. The collected data are arranged in chronological order by month, and image data preprocessing operations such as resizing, normalization, data enhancement, and serialization are performed.

[0102] 3. Remote sensing data collection and preprocessing:

[0103] Use the Google Earth Engine (GEE) platform to collect remote sensing image data of the study area at different times, such as collecting Landsat series data of the Yangtze River Delta region from 2010 to 2022 on a monthly basis. Calculate the land surface temperature (LST) and remote sensing normalized indicators NDVI, NDBI, NDWI and NDBal in the study area. LST is calculated using a single-channel algorithm, and the calculation formula is as follows:

[0104] L λ =M L +DN+A L

[0105]

[0106] T LST =T-273.15

[0107] Where Lλ is the radiation brightness, DN represents the digital value of the thermal infrared band, M L and A L are the correction parameters, which can be found in the metadata file, T is the surface temperature (unit: K), c1 and c2 are Planck constants, which are 1.1910429e -5 [W·m 2 / (sr·μm 4 ) and 1.4387753 [m·μm], λ is the central wavelength of the band (unit: μm), which can be obtained from the metadata file, T LST is the surface temperature (unit: °C).

[0108] The calculation formulas for remote sensing normalized indicators NDVI, NDBI, NDWI and NDBal are as follows:

[0109]

[0110] Among them, nir represents the near infrared band, red represents the infrared band, swir1 represents the shortwave infrared 1 band, and thermal represents the thermal infrared band.

[0111] Step 2: Variable interaction, model construction and selection of potential addresses

[0112] 1. Variable interaction and analysis:

[0113] Variables with strong pairwise correlations are selected to form variable interaction pairs. The variable correlation matrix is ​​constructed using the Pearson correlation analysis method to analyze the possible interaction pairs formed by variables with strong pairwise correlations. Geodetector geographic detectors are established: Factor Detector and Interaction Detector. The factor detector is used to evaluate the explanatory power of each single criterion on the contribution of solar radiation, which is achieved by calculating the q statistic. The interaction detector is used to explore the potential interaction effects between different criteria. By calculating the interaction q statistic of two criteria and comparing it with the q statistic of a single criterion, it is determined whether their interaction relationship is enhanced or weakened. The calculation of the q statistic is as follows:

[0114]

[0115] Where q is a criterion that represents the explanatory power of the response variable Y. In this study, Y refers to the solar radiation DSR; h represents the number of categories of the response variable Y or factor X; N h and N represent the total number of units in the hth class and the total number of units in the entire region, respectively; and σ 2The q statistic ranges from 0 to 1. The larger the q value, the stronger the explanatory power of factor X for Y, and vice versa.

[0116] 2. Linear interaction model construction:

[0117] The forward stepwise regression method was used to gradually add each single factor and pairwise interaction factor into the model, estimate the specific impact of each single factor and pairwise interaction variable on the response variable (solar radiation), and select the one with the highest accuracy (R 2 The model with the highest value is taken as the final interactive linear model. Based on the results of forward stepwise regression, a basic linear model and an interactive linear model are established, and the prediction accuracy of the two is compared. The formulas of the established basic linear model and interactive linear model are as follows:

[0118]

[0119] Among them, y is the response variable, which refers to solar radiation DSR in this study; x i is the i-th factor, β i is the coefficient to be estimated corresponding to each single factor i; x j x k Represents x j and x k The interaction between jk is the estimated coefficient corresponding to each pair of interaction variables; β0 describes the intercept on the y-axis; u is a random error term.

[0120] 3. Model Validation

[0121] In order to ensure the reliability and accuracy of the model, 1000 points were randomly selected for testing, and Cronbach's α coefficient was calculated for model verification. The calculation formula of Cronbach's α coefficient is as follows:

[0122]

[0123] Where k represents the number of items that need to be compared; is the square of the standard deviation of each individual measurement (i.e., the variance), is the square of the population standard deviation.

[0124] 4. Site selection with solar radiation potential

[0125] The study area is divided into several surface grid units, and the established interactive linear model is used to predict the solar radiation data of each studied surface grid unit, and the overall solar radiation distribution map of the study area is drawn. Locations with high solar radiation potential and other suitable conditions are screened out, and these locations are further evaluated to confirm whether they meet the actual construction conditions, such as the convenience of connecting to the power grid and traffic traversal type, and the grid units that meet the conditions are used as alternative grid units.

[0126] Step 3: PV site prediction

[0127] 1.ConvLSTM network construction:

[0128] A prediction model based on the combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) is established. The Conv part is used to extract spatial features, while the LSTM part is used to capture time series features.

[0129] The input data include remote sensing images of the study area at different time periods in the past, the spatial distribution of photovoltaic sites, and the installed capacity of each site. The model will gradually learn the spatiotemporal relationship in these data to more accurately predict the potential distribution of photovoltaic sites.

[0130] 2. Model training and prediction:

[0131] The ConvLSTM model is trained using historical data. During the model training process, the cross-validation method is used to evaluate the performance of the model and adjust model parameters such as learning rate, convolution kernel size, and number of LSTM units.

[0132] After the training is completed, the test data of each time period is input to predict the PV sites, and the output result is the potential distribution map of suitable PV sites and the PV installed capacity of each site.

[0133] Step 4: Regional comprehensive analysis

[0134] 1. Analysis of the impact of urban expansion and economic development:

[0135] Collect remote sensing data from the study area and use GEE to calculate the surface temperature. Analyze the four indicator data of NDVI, NDBI, NDWI, and NDBal. Combined with the historical data of urban agglomeration expansion, quantify the degree of urban expansion. Analyze the trend of urban expansion within the study grid. At the same time, quantify the degree of urban expansion in each study grid area, calculate the expansion area, expansion rate, and expansion intensity, analyze the trend of urban expansion within the study grid, and predict possible future development directions. The calculation formulas for expansion rate and expansion intensity are as follows:

[0136]

[0137] In the formula, ΔU ij is the urban expansion area of ​​the i-th research unit during period j; Δt ij is the time span of period j; ULA ij is the urban area of ​​the ith research unit at the beginning of period j; TLA ij is the total land area of ​​the ith research unit. The urban area in this study is expressed by the urban construction land area.

[0138] Combined with the regional economic development plan, the impact of the construction of photovoltaic sites on the environment is evaluated, such as whether agricultural land and nature reserves will be occupied, so as to avoid negative impacts on the local ecosystem. At the same time, based on the surface cover type data of each candidate grid unit and the expansion trend of urban agglomerations, grid unit areas with small impacts on environmental and economic development are selected from the available photovoltaic site selection sites.

[0139] 2. Comprehensive scoring and address screening:

[0140] The CRITIC-TOPSIS method is used to conduct a more comprehensive evaluation of the remaining effective locations, taking into account solar radiation potential, spatial location and installed capacity of photovoltaic site construction, as well as economic and environmental factors to determine the best location for solar power station construction. The photovoltaic planning construction capacity of the pre-construction unit matches the total photovoltaic installed capacity of the construction unit. Among them, the specific steps used by the CRITIC-TOPSIS method are as follows: 1. Data standardization: For positive indicators (the larger the indicator value, the better), the standardization formula is:

[0141]

[0142] For negative indicators (the smaller the indicator value, the better), the standardized formula is:

[0143]

[0144] Where: x ij is the value of the jth indicator in the ith alternative, r ij is the normalized value.

[0145] 2. CRITIC weight calculation:

[0146] First, calculate the standard deviation σ of each indicator j :

[0147]

[0148] in is the mean of the jth indicator, and m is the number of alternatives.

[0149] Then calculate the correlation coefficient matrix R between the indicatorsjk :

[0150]

[0151] where r ik represents the standardized value of the i-th alternative on the k-th indicator, It represents the mean value of the kth indicator, which is obtained by averaging the standardized values ​​of all alternatives on this indicator. Its calculation formula is as follows:

[0152]

[0153] Next, calculate the weight w of each indicator j :

[0154]

[0155] 3. Construct a weighted decision matrix:

[0156] The element v of the weighted decision matrix ij The calculation formula is:

[0157] v ij =r ij × j

[0158] 4. Calculate the distance between the ideal solution and the negative ideal solution:

[0159] Ideal solution A + and negative ideal solution A - They are:

[0160] A + ={max(v ij )|j=1,2,...,n}

[0161] A - ={min(v ij )|j=1,2,...,n}

[0162] Calculate the distance of each solution to the ideal solution and the negative ideal solution respectively:

[0163]

[0164] 5. Calculate relative proximity:

[0165] Relative proximity The calculation formula is:

[0166]

[0167] 6. Sorting:

[0168] Based on relative proximity Sort the options, the larger the value, the higher the priority, and determine the final optimal construction location.

[0169] Embodiment 2:

[0170] The computer-readable storage medium of this embodiment stores a computer program thereon, and when the program is executed by a processor, the steps in the photovoltaic power station site selection optimization method for urban agglomeration expansion of Example 1 are implemented.

[0171] The computer-readable storage medium of this embodiment may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal; the computer-readable storage medium of this embodiment may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. equipped on the terminal; further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.

[0172] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0173] Embodiment 3:

[0174] The computer device of this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the photovoltaic power station site selection optimization method for urban agglomeration expansion of Example 1 are implemented.

[0175] In this embodiment, the processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, readily available programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0176] Those skilled in the art will appreciate that the disclosed content of the embodiments may be provided as methods, systems, or computer program products. Therefore, the present solution may adopt the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Moreover, the present solution may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0177] The present solution is described with reference to the flowchart and / or block diagram of the method and computer program product according to the embodiment of the present solution. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions; these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0180] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0181] The present invention provides a photovoltaic power station site selection optimization method for urban agglomeration expansion. There are many methods and ways to implement the technical solution. The above is only a preferred implementation of the present invention. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention. All components not specified in this embodiment can be implemented by existing technologies.

Claims

1. A photovoltaic power station site selection optimization method for urban agglomeration expansion, characterized in that: The specific steps are: S1. Acquire data and preprocess the data; S2. Construct interactive linear models and predict addresses with solar radiation potential; S3. Construct a ConvLSTM network and predict potential PV sites and the PV installed capacity of each site; S4. Quantify the extent of urban expansion and select photovoltaic site locations with minimal impact on the environment and economic development based on urban expansion trends and predicted development directions; S5. Use the CRITIC-TOPSIS method to conduct a comprehensive evaluation and determine the best construction site.

2. The optimization method according to claim 1, characterized in that: In S1, the data include terrain data, meteorological data, power grid coverage and transportation network data, photovoltaic sites and photovoltaic installed capacity data in different research areas and different years, and remote sensing data; the preprocessing operations include data cleaning, data deduplication, data deletion, removal of anomalies and noise points, and replacement of anomalies with mean values.

3. The optimization method according to claim 1, characterized in that: The specific steps of S2 are: S21. Interaction and analysis of variables; S22. Construct interactive linear model; S23. Validate the model; S24. Select a site with solar radiation potential.

4. The optimization method according to claim 1, characterized in that: The specific steps of S3 are: S31. Construct ConvLSTM network; S32. Train the ConvLSTM model using historical data, and use the cross-validation method to evaluate the performance of the model and adjust the model parameters; S33. Use the model trained in S32 to predict photovoltaic sites.

5. The optimization method according to claim 1, characterized in that: The specific steps of S4 are: collecting remote sensing data of the study area and using GEE to calculate the surface temperature, analyzing the four indicator data of NDVI, NDBI, NDWI, and NDBal, and combining the historical data of urban agglomeration expansion to quantify the degree of urban expansion; analyzing the trend of urban expansion within the study grid, and quantifying the degree of urban expansion in each study grid area, calculating the expansion area, expansion rate and expansion intensity, analyzing the trend of urban expansion within the study grid, and predicting possible future development directions; combining the regional economic development plan, evaluating the impact of the construction of photovoltaic sites on the environment to avoid negative impacts on the local ecosystem, and at the same time, according to the surface cover type data of each candidate grid unit and the expansion trend of the urban agglomeration, selecting grid unit areas with little impact on the environment and economic development from the available photovoltaic site selection sites.

6. The optimization method according to claim 1, characterized in that: The specific steps of S5 are: using the CRITIC-TOPSIS method to comprehensively evaluate the addresses with solar radiation potential obtained in S2, the potential photovoltaic sites and the photovoltaic installed capacity of each site obtained in S3, and the photovoltaic site selection sites with little impact on the environment and economic development obtained in S4, so as to determine the best location for the construction of the solar power station.

7. The optimization method according to claim 6, characterized in that: The specific steps of the CRITIC-TOPSIS method evaluation are: S51. Data standardization: For positive indicators, the standardization formula is: For negative indicators, the standardized formula is: Where: x ij is the value of the jth indicator in the ith alternative, r ij is the standardized value; S52.CRITIC weight calculation: First, calculate the standard deviation σ of each indicator j : in is the mean of the jth indicator, and m is the number of alternatives; Then calculate the correlation coefficient matrix R between the indicators jk : where r ik represents the standardized value of the i-th alternative on the k-th indicator, It represents the mean value of the kth indicator, which is obtained by averaging the standardized values ​​of all alternatives on this indicator. Its calculation formula is as follows: Next, calculate the weight w of each indicator j : S53. Construct a weighted decision matrix: The element v of the weighted decision matrix ij The calculation formula is: v ij =r ij ×w j S54. Calculate the distance between the ideal solution and the negative ideal solution: Ideal solution A + and negative ideal solution A - They are: A + ={max(v ij )∣j=1,2,...,n} A - ={min(v ij )∣j=1,2,...,n} Calculate the distance of each solution to the ideal solution and the negative ideal solution respectively: S55. Calculate relative proximity: Relative proximity The calculation formula is: S56. Sorting: Based on relative proximity Sort the options, the larger the value, the higher the priority, and determine the final optimal construction location.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the photovoltaic power station site selection optimization method for urban agglomeration expansion as described in any one of claims 1 to 7 are implemented.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the photovoltaic power station site selection optimization method for urban agglomeration expansion according to any one of claims 1 to 7 are implemented.

Images