Optimal site selection method and system for wind and solar power stations based on multi-dimensional evaluation

Abstract

The present invention discloses a method and system for optimizing the site selection of a wind and solar power station based on multi-dimensional evaluation, which relates to the field of renewable energy technology, including: optimizing the target area to be built to obtain a target area that can be built; obtaining the scale information and power supply demand information of the target wind and solar power station; predicting the area occupied by the power station and dividing the target area that can be built; calling the environmental monitoring log to analyze the power supply stability; using the buildable sub-area corresponding to the power supply stability coefficient greater than the power supply stability threshold as the candidate sub-area; using the set of candidate sub-areas as the site selection optimization space, performing sub-area optimization, and obtaining the optimal sub-area; using the optimal sub-area as the site selection area of ​​the target wind and solar power station. The present invention solves the technical problem that the power station location in the prior art is unreasonable, resulting in poor power supply stability and overall power generation quality of the wind and solar power station, and achieves the technical effect of improving the accuracy of site selection of wind and solar power stations, thereby ensuring the power supply stability of the power station and improving the overall power generation quality.

Description

Technical Field

[0001] The present invention relates to the field of renewable energy technology, and in particular to a method and system for optimizing site selection for a wind and solar power station based on multi-dimensional evaluation. Background Art

[0002] In the field of renewable energy, wind energy and solar energy are the two main energy sources. The continuous advancement of technology has gradually reduced the construction cost of wind and solar power stations, which has made large-scale deployment of wind and solar power stations possible. Among them, the site selection of wind and solar power stations directly affects the construction cost, operation efficiency and power supply stability of wind and solar power stations. A good site selection can significantly reduce construction costs, improve power generation efficiency, and ensure the stability of power supply. At present, most site selection methods often only consider natural resources or land properties, while ignoring other important factors, such as environmental impact, economic factors, etc. Therefore, the existing technology has the problem that the location of the power station is unreasonable due to incomplete site selection evaluation and analysis, which in turn causes the power supply stability and overall power generation quality of the wind and solar power station to be poor. Summary of the invention

[0003] This application provides a method and system for optimizing the site selection of wind and solar power stations based on multi-dimensional evaluation, which effectively solves the technical problems in the prior art that the power station location is unreasonable due to incomplete site selection evaluation and analysis, which in turn causes poor power supply stability and overall power generation quality of the wind and solar power stations. This achieves the technical effect of improving the accuracy of site selection for wind and solar power stations, thereby ensuring the power supply stability of the power station and improving the overall power generation quality.

[0004] This application provides a method and system for optimizing the site selection of a wind and solar power station based on multi-dimensional evaluation. The technical solution is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for optimizing the site selection of a wind and solar power station based on multi-dimensional evaluation, the method comprising:

[0006] The target area to be built is optimized based on the preset constraint area to obtain the buildable target area;

[0007] Acquire the scale information and power supply demand information of the target wind and solar power station, wherein the scale information includes wind power installed capacity and photovoltaic installed capacity, and the power supply demand information includes daytime grid-connected power constraints, nighttime grid-connected power constraints and power supply stability threshold;

[0008] Predicting the area occupied by a power station based on the wind power installed capacity and the photovoltaic installed capacity, and dividing the target buildable area based on the power station area to obtain a plurality of buildable sub-areas;

[0009] calling the environmental monitoring logs of the multiple buildable sub-areas, and performing power supply stability analysis based on the environmental monitoring logs, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power, and the nighttime grid-connected power to obtain multiple power supply stability coefficients;

[0010] Taking the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients as candidate sub-regions, to obtain a set of candidate sub-regions;

[0011] Taking the candidate sub-region set as the site selection optimization space, based on the regional fitness evaluation function, performing sub-region optimization in the site selection optimization space to obtain the optimal sub-region, the optimal sub-region is the sub-region with the largest fitness;

[0012] The optimal sub-region is used as the site selection region of the target wind and solar power station.

[0013] In a second aspect, an embodiment of the present application provides a wind and solar power station optimization site selection system based on multi-dimensional evaluation, the system comprising:

[0014] A buildable target area acquisition module, wherein the buildable target area acquisition module is used to optimize the target area to be built based on a preset constraint area to obtain a buildable target area;

[0015] A target wind and solar power station information acquisition module, the target wind and solar power station information acquisition module is used to obtain the scale information and power supply demand information of the target wind and solar power station, the scale information includes wind power installed capacity and photovoltaic installed capacity, the power supply demand information includes daytime grid-connected power constraints, nighttime grid-connected power constraints and power supply stability threshold;

[0016] A plurality of constructible sub-area acquisition modules, wherein the plurality of constructible sub-area acquisition modules are used to predict the area occupied by a power station based on the wind power installed capacity and the photovoltaic installed capacity, and to divide the constructible target area based on the power station area to obtain a plurality of constructible sub-areas;

[0017] A power supply stability analysis module, the power supply stability analysis module is used to call the environmental monitoring logs of the multiple buildable sub-areas, and perform power supply stability analysis based on the environmental monitoring logs, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power and the nighttime grid-connected power to obtain multiple power supply stability coefficients;

[0018] A candidate sub-region set acquisition module, the candidate sub-region set acquisition module is used to take the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients as candidate sub-regions, to obtain a candidate sub-region set;

[0019] A sub-region optimization module, wherein the sub-region optimization module is used to use the candidate sub-region set as a location optimization space, and based on a regional fitness evaluation function, perform sub-region optimization in the location optimization space to obtain an optimal sub-region, wherein the optimal sub-region is a sub-region with the largest fitness;

[0020] A site selection area determination module, the site selection area determination module is used to use the optimal sub-area as the site selection area of ​​the target wind and solar power station.

[0021] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0022] The present application first optimizes the target area to be built based on the preset constraint area to obtain the buildable target area, and then obtains the scale information and power supply demand information of the target wind and solar power station, the scale information includes the wind power installed capacity and the photovoltaic installed capacity, and the power supply demand information includes the daytime grid-connected power constraint, the nighttime grid-connected power constraint and the power supply stability threshold, and then predicts the power station area based on the wind power installed capacity and the photovoltaic installed capacity, and divides the buildable target area based on the power station area to obtain multiple buildable sub-areas, and then calls the environmental monitoring logs of the multiple buildable sub-areas, and based on the environmental monitoring logs, the The wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power and the nighttime grid-connected power are analyzed for power supply stability to obtain multiple power supply stability coefficients, and then the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients are used as candidate sub-regions to obtain a set of candidate sub-regions. The set of candidate sub-regions is used as the site selection optimization space, and based on the regional fitness evaluation function, sub-region optimization is performed in the site selection optimization space to obtain the optimal sub-region, which is the sub-region with the largest fitness. Finally, the optimal sub-region is used as the site selection area of ​​the target wind and solar power station. The technical problem that the unreasonable location of the power station due to the incomplete site selection evaluation analysis in the prior art is effectively solved, and the power supply stability and overall power generation quality of the wind and solar power station are poor, and the accuracy of the site selection of the wind and solar power station is improved, thereby ensuring the power supply stability of the power station and improving the overall power generation quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1A schematic diagram of a flow chart of a method for optimizing site selection for a wind and solar power station based on multi-dimensional evaluation provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a flow chart of a method for obtaining multiple power supply stability coefficients provided in an embodiment of the present application;

[0026] Figure 3 A schematic diagram of a flow chart of a method for obtaining a first power supply stability coefficient provided in an embodiment of the present application;

[0027] Figure 4 A schematic diagram of a flow chart of a method for obtaining an optimal sub-region provided in an embodiment of the present application;

[0028] Figure 5 A schematic diagram of a method for determining a potential risk factor provided in an embodiment of the present application;

[0029] Figure 6 A schematic diagram of the structure of a wind and solar power station optimization site selection system based on multi-dimensional evaluation provided in an embodiment of the present application.

[0030] Explanation of the reference numerals: module for acquiring target areas that can be built 1, module for acquiring information of target wind and solar power stations 2, module for acquiring multiple sub-areas that can be built 3, module for analyzing power supply stability 4, module for acquiring a set of candidate sub-areas 5, module for optimizing sub-areas 6, and module for determining a site selection area 7. DETAILED DESCRIPTION

[0031] The present application provides a method and system for optimizing the site selection of a wind and solar power station based on a multi-dimensional evaluation, which is used to solve the technical problem in the prior art that the power station location is unreasonable due to incomplete site selection evaluation and analysis, which in turn causes poor power supply stability and overall power generation quality of the wind and solar power station.

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0033] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] like Figure 1 As shown, the present invention provides a method for optimizing the site selection of a wind and solar power station based on multi-dimensional evaluation, which is used to improve the accuracy of the site selection of a wind and solar power station, thereby ensuring the power supply stability of the power station and improving the overall power generation quality. The method includes:

[0036] Pre-set constraint areas, which refer to specific areas that are pre-set during the site selection process and require special consideration or avoidance of construction. These areas are deemed unconstructable due to specific protection needs, environmental impacts or other constraints, and include ecological protection areas, water source protection areas, nature reserves, military areas, basic farmland protection areas, etc. The specific location and scope of the constraint area are determined through analysis of resource assessment, geographic information system analysis, environmental sensitivity assessment, land use planning and urban planning. According to the preset constraint area, a multi-objective optimization method is adopted to comprehensively consider multiple factors such as resource conditions, construction conditions, safety requirements, and grid access conditions. By setting optimization goals (such as maximizing resource utilization, minimizing environmental impact, etc.) and constraint conditions (such as meeting grid needs, avoiding ecological protection areas, etc.), the target area to be built is optimized. The target area to be built refers to the potential construction area determined in the site selection process, which has potential construction conditions and possibilities, including areas with wind and solar energy resources, suitable terrain and landform features, and areas that meet other construction conditions. After evaluation and optimization in the target area to be built, the area that can be constructed is determined, and the area is used as a buildable target area (feasible construction area). The buildable target area is a candidate area for further power station design and construction.

[0037] Determine the target wind and solar power station, the target wind and solar power station refers to the planned wind and solar power station for combined power generation, and determine the scale information and power supply demand information of the target wind and solar power station by methods such as site survey, resource assessment, market demand analysis, and communication with power companies and relevant institutions, wherein the scale information is a parameter used to describe the size of the power station, including wind power installed capacity and photovoltaic installed capacity. The wind power installed capacity refers to the designed installed capacity of the wind turbine generator set, which indicates the maximum power generation capacity of the wind power station under normal working conditions, and the photovoltaic installed capacity refers to the designed installed capacity of the photovoltaic power station, which indicates the maximum power generation capacity of the photovoltaic power station under normal working conditions. The maximum power generation capacity of the station; the power supply demand information is used to describe the parameters of the power supply demand of the power station, including the grid-connected power constraints during the day and at night and the power supply stability threshold. The daytime grid-connected power constraint refers to the restrictions or regulations on the power transmitted to the power grid by the wind and solar power stations during the daytime period, and the nighttime grid-connected power constraint refers to the restrictions or regulations on the power transmitted to the power grid by the wind and solar power stations during the nighttime period. The power supply stability threshold is a standard or threshold for measuring power supply stability. It is set according to the power supply demand survey results and the stable operation requirements of the power grid. If the power supply stability of the wind and solar power stations exceeds this threshold, it is considered that it meets the power supply stability requirements.

[0038] According to the technical parameters of wind power and photovoltaic power (such as the rated power and floor area of ​​each wind turbine, and the power and layout density of photovoltaic panels, etc.), a prediction model for the floor area of ​​wind power and photovoltaic power generation is established. The model is based on industry standards or historical data and comprehensively considers the impact of factors such as terrain, landform, and climate conditions on the floor area. According to the known installed capacity of wind power and photovoltaic power, the estimated floor area of ​​the corresponding wind power station and photovoltaic power station is calculated through the floor area prediction model. Based on the predicted floor area of ​​the power station and the analysis of the target area that can be built, including the continuity of the terrain and landform, soil conditions, necessary infrastructure, potential ecological and environmental impacts, traffic conditions, etc., the suitability of these areas for the construction of wind power and photovoltaic power stations is evaluated. Through analysis, the target area that can be built is divided into multiple sub-areas that can be built, each of which has a clear boundary and area, and the area is greater than or equal to the predicted floor area of ​​the power station.

[0039] Through the data center or cloud platform, the environmental monitoring log data of multiple buildable sub-areas are called and integrated, and the environmental monitoring log includes meteorological conditions (such as wind speed, wind direction, temperature, humidity, solar radiation, etc.), environmental pollutant concentration, noise level, etc. Based on the environmental monitoring log, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power and the nighttime grid-connected power, a power supply stability analysis model is established, and the model comprehensively considers factors such as the instability of wind and solar energy, the stability requirements of the power grid, and the configuration of energy storage equipment. Using the established power supply stability analysis model, the environmental monitoring log data of each buildable sub-area is processed and analyzed, including evaluating the stability of the output power of wind power and photovoltaic power generation, predicting the change trend of the power grid load, analyzing the charging and discharging strategy of the energy storage equipment, etc. According to the analysis results, based on the power fluctuation amplitude, frequency, duration and other indicators, the power supply stability coefficient of each buildable sub-area is calculated, and the coefficient is used to measure the power supply stability level of each sub-area. Traverse multiple power supply stability coefficients, and select the buildable sub-areas corresponding to the power supply stability coefficient greater than the power supply stability threshold for sorting and summarization to form a set of candidate sub-areas.

[0040] The set of candidate sub-regions is used as the site selection optimization space, and a regional fitness evaluation function is defined. This function comprehensively considers various factors such as land conditions, resource availability, environmental impact, economic benefits, etc., and is used to comprehensively evaluate the adaptability of each sub-region. Within the set of candidate sub-regions, each sub-region is evaluated using the regional fitness evaluation function. By calculating the fitness value of each sub-region, the sub-region with the largest fitness value is found. This sub-region is the optimal sub-region. The optimal sub-region has the highest comprehensive adaptability and can meet the construction requirements of wind power and photovoltaic power stations to the greatest extent. The optimal sub-region is used as the final site selection area for the target wind and photovoltaic power station. The embodiment of the present application makes the site selection decision more accurate and reliable by comprehensively considering multiple dimensions and quantitative evaluation indicators, thereby achieving the technical effect of improving the accuracy of site selection, thereby ensuring the stability of power supply to the power station and improving the overall power generation quality.

[0041] like Figure 2 As shown, in a preferred implementation manner provided in an embodiment of the present application, the power supply stability analysis is performed based on the environmental monitoring log, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power constraint and the nighttime grid-connected power constraint to obtain multiple power supply stability coefficients, and further includes:

[0042] Select one from multiple buildable sub-areas as the analysis object, i.e., the first buildable sub-area, and obtain the environmental monitoring log of the sub-area (the first environmental monitoring log), which includes first sunshine intensity monitoring data and first wind speed monitoring data. The sunshine intensity monitoring data records the solar light intensity data of the first buildable sub-area, reflecting the sunshine changes in different seasons and at different times. The wind speed monitoring data records the wind speed data of the first buildable sub-area, reflecting the wind speed distribution, wind direction changes and other information in the area.

[0043] In order to more accurately analyze the fluctuation of power generation, the first sunshine intensity monitoring data and the first wind speed monitoring data are processed and divided according to the time granularity to obtain sunshine intensity sets (first sunshine intensity sets) and wind speed sets (first wind speed sets) corresponding to multiple time granularities (such as hours, days, months, etc.). For example, the sunshine intensity or wind speed data of a day can be divided into different granularities such as one data point per hour and one data point per half hour.

[0044] By using multiple divided sunshine intensity sets and wind speed sets, combined with wind power installed capacity and photovoltaic installed capacity, the power generation is predicted through a prediction model or algorithm, and the predicted power generation at each time granularity (first predicted power generation) is calculated. These predicted power values ​​reflect the power generation capacity under different environmental conditions.

[0045] According to the obtained predicted power generation corresponding to the multiple time granularities and the corresponding relationship between the multiple time granularities, a power generation chronology (first power generation chronology) is constructed, and the chronology shows the predicted power generation in different time periods within a year.

[0046] Based on the constructed power generation chronology, combined with the daytime grid-connected power constraints and the nighttime grid-connected power constraints, the analysis is performed, and the power supply stability analysis is performed using the daytime grid-connected power constraints and the nighttime grid-connected power constraints as stability evaluation indicators. By comparing the difference between the predicted power generation and the grid-connected power constraints, the stability of the power supply is evaluated. The smaller the difference, the higher the power supply stability. According to the results of the power supply stability analysis, combined with factors such as the power generation fluctuation and the degree of satisfaction of the grid-connected power constraints, the first power supply stability coefficient is calculated, which quantifies the power supply stability of the first buildable sub-area.

[0047] Repeat the above steps, analyze each buildable sub-area, calculate the respective power supply stability coefficient, and finally obtain the power supply stability coefficient corresponding to each buildable sub-area to form a set of power supply stability coefficients. This preferred implementation method divides the environmental monitoring data into different time granularities through granularity division, and performs power generation prediction on this basis, which can more accurately predict the power generation of wind power or photovoltaic power stations, and comprehensively evaluate the performance of wind power or photovoltaic power station power generation capacity on different time scales, providing a reliable data basis for power supply stability analysis, thereby achieving the technical effect of accurately evaluating the stability and reliability of power supply.

[0048] In another preferred implementation manner provided in the embodiment of the present application, the power generation prediction is performed based on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first predicted power generation powers, further comprising:

[0049] A power generation prediction model is constructed using a BP neural network, and the prediction model includes a photovoltaic power generation prediction branch and a wind power generation prediction branch. The photovoltaic power generation prediction branch is used to predict the power generation of multiple first sunshine intensity sets, and the sunshine intensity data is input. The photovoltaic power generation power at each time granularity is calculated through the model to obtain multiple first photovoltaic power generation power sets, and each set corresponds to a specific time granularity. The wind power generation prediction branch is used to predict the power generation of multiple first wind speed sets, and the wind speed data is used as input. The wind power generation power at each time granularity is calculated through the model to obtain multiple first wind power generation power sets.

[0050] In order to smooth the prediction results and reduce the impact of accidental fluctuations on the analysis, the first photovoltaic power generation set and the first wind power generation set at each time granularity are averaged to obtain multiple first photovoltaic power generation power means and multiple first wind power generation power means, which represent the average power generation at each time granularity.

[0051] The first photovoltaic power generation mean and the first wind power generation mean at each time granularity are added and summed to obtain multiple first predicted power generation, each corresponding to a specific time granularity, so as to realize the combined predicted power of photovoltaic power generation and wind power generation, thereby obtaining the overall predicted power generation of the first buildable sub-area. This preferred implementation method predicts photovoltaic and wind power generation by constructing a BP neural network model, thereby improving the accuracy of the prediction, reducing the impact of accidental fluctuations on the prediction results by calculating the mean, making the prediction results smoother and more reliable, and achieving the technical effect of obtaining a more accurate predicted power generation.

[0052] like Figure 3As shown, in another preferred implementation manner provided in the embodiment of the present application, based on the first power generation power chronology, the power supply stability analysis is performed with the daytime grid-connected power constraint and the nighttime grid-connected power constraint as stability evaluation indicators to obtain a first power supply stability coefficient, and further includes:

[0053] According to the daytime grid-connected power constraints and the nighttime grid-connected power constraints, each first predicted power generation in the first power generation chronology is judged to check whether the predicted power generation at each time granularity meets the corresponding daytime or nighttime grid-connected power constraints.

[0054] If the first predicted power generation does not meet the corresponding grid-connected power constraint (daytime grid-connected power constraint or nighttime grid-connected power constraint), the fluctuating power supply is marked once at this time granularity, indicating that there is power supply fluctuation. By counting the number of marks, the daytime fluctuating power supply ratio and the nighttime fluctuating power supply ratio are calculated.

[0055] The weight of daytime power supply is set as the first weight, and the weight of nighttime power supply is set as the second weight, which is used to reflect the importance of power supply stability in different time periods. Due to the different importance or demand during the day and at night, the value of the first weight is set to be greater than the second weight.

[0056] Based on the set first weight and second weight, the proportion of fluctuating power supply during the day and the proportion of fluctuating power supply at night are weightedly calculated. The result of the weighted calculation reflects the degree of power supply fluctuation at different time granularities. The inverse of the weighted calculation result is used as the first power supply stability coefficient, which quantifies the stability of the power supply. The larger the coefficient value, the higher the power supply stability. This preferred implementation method evaluates the predicted generated power through the grid-connected power constraint, avoids overestimation or underestimation of power supply stability, and thus achieves the technical effect of improving the accuracy of stability evaluation.

[0057] like Figure 4 As shown, in another preferred implementation provided by the embodiment of the present application, the sub-region optimization is performed in the site selection optimization space based on the regional fitness evaluation function to obtain the optimal sub-region, and further includes:

[0058] The first sub-region and the second sub-region are randomly selected without replacement in the site optimization space to ensure that each sub-region has a chance to be selected. The fitness of the first sub-region and the second sub-region is evaluated using the regional fitness evaluation function to obtain the first fitness and the second fitness, which represent the comprehensive adaptability of the two sub-regions.

[0059] The first fitness is compared with the second fitness. If the first fitness is less than or equal to the second fitness, the second sub-region is used as the current optimal sub-region. When the first fitness is greater than the second fitness, a certain probability is set to select the second sub-region as the current optimal sub-region. The probability decreases with the increase of the number of optimization iterations. The probability setting is used to improve the global search capability in the early stage of optimization, jump out of the local optimum, and speed up the optimization speed. In the later stage of optimization, the search range is narrowed to improve the accuracy of the optimization results.

[0060] Repeat the above steps until the current optimization number meets the preset optimization constraint, which is a fixed number of iterations or a judgment based on a certain convergence condition. In each iteration, the current optimal sub-region is determined based on fitness comparison and probability selection, and the current optimal sub-region finally output is the final optimal sub-region, which is determined after multiple iterations and comparisons in a given location optimization space and has the highest comprehensive adaptability. This preferred implementation ensures that each sub-region has a chance to be selected by randomly selecting the first sub-region and the second sub-region without replacement in the location optimization space, and by setting a certain probability to select the second sub-region as the current optimal sub-region in the early stage of optimization, it avoids falling into the local optimal solution and speeds up the optimization speed. In the later stage of optimization, by reducing the probability of selecting the second sub-region, the search range is narrowed and the accuracy of the optimization result is improved, thereby achieving a technical effect of balancing global search and local search and improving optimization speed and accuracy.

[0061] In another preferred implementation provided in the examples of the present application, the method further comprises:

[0062] The regional fitness evaluation function is:

[0063]

[0064] Where F(i) is the fitness of the ith sub-region, n1 is the first weight, n2 is the second weight, n3 is the third weight, the sum of n1, n2, and n3 is 1, and W i is the total power generation of the ith sub-region, P i is the installation convenience of the ith sub-area, which is related to factors such as topography and landform. i is the potential risk coefficient of the ith sub-region.

[0065] like Figure 5 As shown, in another preferred implementation manner provided in the embodiments of the present application, the method further includes:

[0066] Risk event data of multiple wind and solar power stations are collected through the operation records, accident reports, maintenance records, etc. of existing wind and solar power stations, including equipment failures, natural disasters, human errors, etc.

[0067] The accident tree principle is used to trace the source of risk events, and a logical analysis is conducted on the causes and conditions that may lead to each risk event. The series of causes and conditions that lead to the event are determined, and risk factors are identified, including equipment failure, human error, natural disasters, environmental factors, etc. After tracing the risk events of multiple wind and solar power stations, a series of risk factor sets are obtained, including risk factors related to equipment, risk factors related to human operations, risk factors related to natural disasters, etc.

[0068] Frequency analysis is performed on the obtained risk factor set, and the frequency of occurrence of each risk factor in multiple risk events is counted to determine the probability of its occurrence and the degree of impact. After frequency analysis, frequent risk factors are determined, that is, these risk factors frequently appear in multiple risk events and may have a greater impact on the operation of wind and solar power stations.

[0069] The historical environmental monitoring data of the sub-region is collected within a preset time period, including meteorological data, environmental conditions, etc. Based on the determined frequent risk factors, the historical environmental monitoring data is counted and analyzed, and the number and frequency of frequent risk factors in each sub-region within the preset time period are counted. According to the statistical results, the risk of each sub-region is comprehensively evaluated based on the number, frequency, duration and other factors of the frequent risk factors to obtain a potential risk coefficient. The potential risk coefficient is a comprehensive evaluation indicator used to quantify the comprehensive risk level of the sub-region. The higher the potential risk coefficient, the greater the risk of the sub-region. This preferred embodiment provides a quantitative evaluation indicator for the risk of the sub-region through the determination of the potential risk coefficient, which helps to accurately compare the risk levels of different sub-regions, thereby achieving the technical effect of providing a scientific basis for site selection decisions.

[0070] Embodiment 2

[0071] Based on the same inventive concept as the method for optimizing the site selection of a wind and solar power station based on multi-dimensional evaluation in the aforementioned embodiment, Figure 6 As shown, the present application provides a wind and solar power station optimization site selection system based on multi-dimensional evaluation, the system comprising:

[0072] A buildable target area acquisition module 1, wherein the buildable target area acquisition module 1 is used to optimize the target area to be built based on a preset constraint area to obtain a buildable target area;

[0073] Target wind and solar power station information acquisition module 2, the target wind and solar power station information acquisition module 2 is used to obtain the scale information and power supply demand information of the target wind and solar power station, the scale information includes wind power installed capacity and photovoltaic installed capacity, the power supply demand information includes daytime grid-connected power constraints, nighttime grid-connected power constraints and power supply stability threshold;

[0074] A plurality of constructible sub-area acquisition modules 3, wherein the plurality of constructible sub-area acquisition modules 3 are used to predict the area occupied by a power station based on the wind power installed capacity and the photovoltaic installed capacity, and to divide the constructible target area based on the power station area to obtain a plurality of constructible sub-areas;

[0075] A power supply stability analysis module 4, the power supply stability analysis module 4 is used to call the environmental monitoring logs of the multiple buildable sub-areas, and perform power supply stability analysis based on the environmental monitoring logs, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power and the nighttime grid-connected power to obtain multiple power supply stability coefficients;

[0076] A candidate sub-region set acquisition module 5, wherein the candidate sub-region set acquisition module 5 is used to select the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients as candidate sub-regions to obtain a candidate sub-region set;

[0077] A sub-region optimization module 6, wherein the sub-region optimization module 6 is used to use the candidate sub-region set as a location optimization space, perform sub-region optimization in the location optimization space based on a regional fitness evaluation function, and obtain an optimal sub-region, wherein the optimal sub-region is a sub-region with the largest fitness;

[0078] The site selection area determination module 7 is used to use the optimal sub-area as the site selection area of ​​the target wind and solar power station.

[0079] Furthermore, the power supply stability analysis module 4 is used to perform the following method:

[0080] Selecting a first buildable sub-area from the multiple buildable sub-areas, and acquiring a first environment monitoring log of the first buildable sub-area, wherein the first environment monitoring log includes first sunshine intensity monitoring data and first wind speed monitoring data;

[0081] Performing granularity division on the first sunshine intensity monitoring data and the first wind speed monitoring data to obtain a plurality of first sunshine intensity sets and a plurality of first wind speed sets corresponding to a plurality of time granularities;

[0082] Perform power generation prediction based on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first predicted power generation powers;

[0083] Constructing a first power generation chronology according to the mapping relationship between the multiple time granularities and the multiple first predicted power generation powers;

[0084] Based on the first power generation power chronology, power supply stability analysis is performed using the daytime grid-connected power constraint and the nighttime grid-connected power constraint as stability evaluation indicators to obtain a first power supply stability coefficient;

[0085] A plurality of power supply stability coefficients are obtained based on the first power supply stability coefficient.

[0086] Furthermore, the power supply stability analysis module 4 is used to perform the following method:

[0087] The photovoltaic power generation prediction branch and the wind power generation prediction branch sequentially perform power generation prediction on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first photovoltaic power generation sets and multiple first wind power generation sets;

[0088] Calculating the averages of the plurality of first photovoltaic power sets and the plurality of first wind power sets to obtain the plurality of first photovoltaic power averages and the plurality of first wind power averages;

[0089] The multiple first photovoltaic power generation power averages and the multiple first wind power generation power averages are added and summed to obtain multiple first predicted power generation powers.

[0090] Furthermore, the power supply stability analysis module 4 is used to perform the following method:

[0091] Judging a plurality of first predicted power generation powers in the first power generation power chronology according to the daytime grid-connected power constraint and the nighttime grid-connected power constraint;

[0092] When the first predicted power generation power does not satisfy the corresponding daytime grid-connected power constraint or the nighttime grid-connected power constraint, the current time granularity is marked with a fluctuating power supply to obtain a daytime fluctuating power supply ratio and a nighttime fluctuating power supply ratio;

[0093] Obtaining a first weight of daytime power supply and a second weight of nighttime power supply, wherein the first weight is greater than the second weight;

[0094] The daytime fluctuating power supply ratio and the nighttime fluctuating power supply ratio are weightedly calculated based on the first weight and the second weight, and the inverse of the weighted calculation result is used as a first power supply stability coefficient.

[0095] Furthermore, the sub-region optimization module 6 is used to perform the following method:

[0096] Randomly selecting a first sub-region and a second sub-region without replacement in the location optimization space;

[0097] Performing fitness evaluation on the first sub-region and the second sub-region according to the regional fitness evaluation function to obtain a first fitness and a second fitness;

[0098] Comparing the first fitness with the second fitness, and when the first fitness is less than or equal to the second fitness, taking the second sub-region as the current optimal sub-region;

[0099] When the first fitness is greater than the second fitness, the second sub-region is used as the current optimal sub-region according to probability, wherein the probability decreases as the number of optimization iterations increases;

[0100] Iterate the optimization until the current number of optimizations meets the preset optimization constraints, and output the current optimal sub-region as the optimal sub-region.

[0101] Furthermore, the sub-region optimization module 6 is used to perform the following method:

[0102] The regional fitness evaluation function is:

[0103]

[0104] Where F(i) is the fitness of the ith sub-region, n1 is the first weight, n2 is the second weight, n3 is the third weight, the sum of n1, n2, and n3 is 1, and W i is the total power generation of the ith sub-region, P i is the installation convenience of the ith sub-area, S i is the potential risk coefficient of the ith sub-region.

[0105] Furthermore, the sub-region optimization module 6 is used to perform the following method:

[0106] Obtain risk events of multiple wind and solar power stations;

[0107] Based on the principle of accident tree, the risk events of the multiple wind and solar power stations are traced and analyzed to obtain multiple risk factor sets;

[0108] Performing a risk factor frequency analysis based on the multiple risk factor sets to determine multiple frequent risk factors;

[0109] Based on the multiple frequent risk factors, frequent risk factor statistics are performed on the historical environmental monitoring data of the sub-area within a preset time period, and a potential risk coefficient is determined according to the statistical results.

[0110] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0112] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for optimizing the site selection of wind and solar power stations based on multi-dimensional evaluation, characterized in that: The method comprises: The target area to be built is optimized based on the preset constraint area to obtain a buildable target area; Acquire the scale information and power supply demand information of the target wind and solar power station, wherein the scale information includes wind power installed capacity and photovoltaic installed capacity, and the power supply demand information includes daytime grid-connected power constraints, nighttime grid-connected power constraints and power supply stability threshold; Predicting the area occupied by a power station based on the wind power installed capacity and the photovoltaic installed capacity, and dividing the target buildable area based on the power station area to obtain a plurality of buildable sub-areas; calling the environmental monitoring logs of the multiple buildable sub-areas, and performing power supply stability analysis based on the environmental monitoring logs, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power, and the nighttime grid-connected power to obtain multiple power supply stability coefficients; Taking the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients as candidate sub-regions, to obtain a set of candidate sub-regions; Taking the candidate sub-region set as the site selection optimization space, based on the regional fitness evaluation function, performing sub-region optimization in the site selection optimization space to obtain the optimal sub-region, the optimal sub-region is the sub-region with the largest fitness; Using the optimal sub-region as the site selection region of the target wind and solar power station; The power supply stability analysis is performed based on the environmental monitoring log, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power constraint and the nighttime grid-connected power constraint to obtain multiple power supply stability coefficients, and further includes: Selecting a first buildable sub-area from the multiple buildable sub-areas, and acquiring a first environment monitoring log of the first buildable sub-area, wherein the first environment monitoring log includes first sunshine intensity monitoring data and first wind speed monitoring data; Performing granularity division on the first sunshine intensity monitoring data and the first wind speed monitoring data to obtain a plurality of first sunshine intensity sets and a plurality of first wind speed sets corresponding to a plurality of time granularities; Perform power generation prediction based on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first predicted power generation powers; Constructing a first power generation chronology according to the mapping relationship between the multiple time granularities and the multiple first predicted power generation powers; Based on the first power generation power chronology, power supply stability analysis is performed using the daytime grid-connected power constraint and the nighttime grid-connected power constraint as stability evaluation indicators to obtain a first power supply stability coefficient; Obtaining multiple power supply stability coefficients based on the first power supply stability coefficient; The method of performing power generation prediction based on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first predicted power generation powers further includes: The photovoltaic power generation prediction branch and the wind power generation prediction branch sequentially perform power generation prediction on the multiple first sunshine intensity sets and the multiple first wind speed sets to obtain multiple first photovoltaic power generation sets and multiple first wind power generation sets; Calculating the averages of the plurality of first photovoltaic power sets and the plurality of first wind power sets to obtain the plurality of first photovoltaic power averages and the plurality of first wind power averages; Adding and summing the plurality of first photovoltaic power generation averages and the plurality of first wind power generation averages to obtain a plurality of first predicted power generation; The step of performing power supply stability analysis based on the first power generation power chronology and taking the daytime grid-connected power constraint and the nighttime grid-connected power constraint as stability evaluation indicators to obtain a first power supply stability coefficient also includes: Judging a plurality of first predicted power generation powers in the first power generation power chronology according to the daytime grid-connected power constraint and the nighttime grid-connected power constraint; When the first predicted power generation power does not satisfy the corresponding daytime grid-connected power constraint or the nighttime grid-connected power constraint, the current time granularity is marked with a fluctuating power supply to obtain a daytime fluctuating power supply ratio and a nighttime fluctuating power supply ratio; Obtaining a first weight of daytime power supply and a second weight of nighttime power supply, wherein the first weight is greater than the second weight; The daytime fluctuating power supply ratio and the nighttime fluctuating power supply ratio are weightedly calculated based on the first weight and the second weight, and the inverse of the weighted calculation result is used as a first power supply stability coefficient.

2. The method according to claim 1, characterized in that The method of performing sub-region optimization in the site selection optimization space based on the regional fitness evaluation function to obtain the optimal sub-region also includes: Randomly selecting a first sub-region and a second sub-region without replacement in the location optimization space; Performing fitness evaluation on the first sub-region and the second sub-region according to the regional fitness evaluation function to obtain a first fitness and a second fitness; Comparing the first fitness with the second fitness, and when the first fitness is less than or equal to the second fitness, taking the second sub-region as the current optimal sub-region; When the first fitness is greater than the second fitness, the second sub-region is used as the current optimal sub-region according to probability, wherein the probability decreases as the number of optimization iterations increases; Iterate the optimization until the current number of optimizations meets the preset optimization constraints, and output the current optimal sub-region as the optimal sub-region.

3. The method according to claim 2, characterized in that The method further comprises: The regional fitness evaluation function is: Where F(i) is the fitness of the ith sub-region, n1 is the first weight, n2 is the second weight, n3 is the third weight, the sum of n1, n2, and n3 is 1, and W i is the total power generation of the ith sub-region, P i is the installation convenience of the ith sub-area, S i is the potential risk coefficient of the ith sub-region.

4. The method according to claim 3, characterized in that The method further comprises: Obtain risk events of multiple wind and solar power stations; Based on the principle of accident tree, the risk events of the multiple wind and solar power stations are traced and analyzed to obtain multiple risk factor sets; Performing a risk factor frequency analysis based on the multiple risk factor sets to determine multiple frequent risk factors; Based on the multiple frequent risk factors, frequent risk factor statistics are performed on the historical environmental monitoring data of the sub-area within a preset time period, and a potential risk coefficient is determined according to the statistical results.

5. The wind and solar power station optimization site selection system based on multi-dimensional evaluation is characterized by: For executing the method according to any one of claims 1 to 4, the system comprises: A buildable target area acquisition module, wherein the buildable target area acquisition module is used to optimize the target area to be built based on a preset constraint area to obtain a buildable target area; A target wind and solar power station information acquisition module, the target wind and solar power station information acquisition module is used to obtain the scale information and power supply demand information of the target wind and solar power station, the scale information includes wind power installed capacity and photovoltaic installed capacity, the power supply demand information includes daytime grid-connected power constraints, nighttime grid-connected power constraints and power supply stability threshold; A plurality of constructible sub-area acquisition modules, wherein the plurality of constructible sub-area acquisition modules are used to predict the area occupied by a power station based on the wind power installed capacity and the photovoltaic installed capacity, and to divide the constructible target area based on the power station area to obtain a plurality of constructible sub-areas; A power supply stability analysis module, the power supply stability analysis module is used to call the environmental monitoring logs of the multiple buildable sub-areas, and perform power supply stability analysis based on the environmental monitoring logs, the wind power installed capacity, the photovoltaic installed capacity, the daytime grid-connected power and the nighttime grid-connected power to obtain multiple power supply stability coefficients; A candidate sub-region set acquisition module, the candidate sub-region set acquisition module is used to take the buildable sub-regions corresponding to the power supply stability coefficients greater than the power supply stability threshold among the multiple power supply stability coefficients as candidate sub-regions, to obtain a candidate sub-region set; A sub-region optimization module, wherein the sub-region optimization module is used to use the candidate sub-region set as a location optimization space, perform sub-region optimization in the location optimization space based on a regional fitness evaluation function, and obtain an optimal sub-region, wherein the optimal sub-region is a sub-region with the largest fitness; A site selection area determination module is used to use the optimal sub-area as the site selection area of ​​the target wind and solar power station.

Images