Soil salinity regulation method and device under vertical photovoltaic array

Abstract

The application provides a soil salinity regulation method and device under a vertical photovoltaic array, comprising: collecting photovoltaic parameters of the vertical photovoltaic array and soil monitoring indexes of each monitoring unit of the vertical photovoltaic array; inputting the photovoltaic parameters and the soil monitoring indexes into a pre-trained soil salinity prediction model to obtain salinity prediction results of each monitoring unit of the vertical photovoltaic array; and determining corresponding irrigation modes and plant varieties of each monitoring unit based on the salinity prediction results. The application improves the ecological restoration efficiency and land utilization efficiency of the vertical photovoltaic power station.

Description

Technical Field

[0001] This invention relates to the field of ecological restoration and agricultural planting technology of photovoltaic power plants, and in particular to a method and device for soil salinity regulation under a vertical photovoltaic array. Background Technology

[0002] Vertical photovoltaic (PV) arrays, as a novel photovoltaic structure, have addressed the shortcomings of insufficient power generation in traditional vertical installations through technological breakthroughs such as crystal orientation optimization. Their unique vertical shading structure can alter local microclimates, reducing wind speed and increasing soil moisture and cooling, thus offering new possibilities for soil salinity regulation. However, the asymmetric shading characteristics of vertical PV arrays result in complex spatiotemporal heterogeneity in soil water, heat, and salt distribution, significantly different from the horizontal shading of traditional fixed PV arrays. Existing technologies struggle to accurately predict salinity distribution patterns, making them unsuitable for brackish water irrigation and salt-tolerant plant configurations in vertical PV arrays. Consequently, the ecological restoration and land use efficiency of vertical PV power plants remains low. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method and apparatus for regulating soil salinity under a vertical photovoltaic array, so as to improve the ecological restoration efficiency and land use efficiency of vertical photovoltaic power stations.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a method for regulating soil salinity under a vertical photovoltaic array, comprising: collecting photovoltaic parameters of the vertical photovoltaic array and soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; inputting the photovoltaic parameters and soil monitoring indicators into a pre-trained soil salinity prediction model to obtain salinity prediction results for each monitoring unit of the vertical photovoltaic array; and determining the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results.

[0005] Optionally, the salinity prediction results include: salinity content and salinity accumulation rate within a preset time period; based on the salinity prediction results, determine the corresponding irrigation mode and plant species for each monitoring unit, including: based on salinity content, determine the soil salinity risk level of each monitoring unit of the vertical photovoltaic array, and based on the soil salinity risk level, determine the irrigation mode of each monitoring unit; based on the salinity accumulation rate, determine the plant species for each monitoring unit.

[0006] Optionally, the soil salinity risk level includes: low risk, medium risk, and high risk; the irrigation mode for each monitoring unit is determined based on the soil salinity risk level, including: if the soil salinity risk level is low, the original brackish water is used for irrigation; if the soil salinity risk level is medium, the original brackish water is mixed with desalinated water driven by photovoltaic power generation in a preset ratio for irrigation; if the soil salinity risk level is high, desalinated water is used for irrigation.

[0007] Optionally, the plant species for each monitoring unit can be determined based on the salt accumulation rate, including: if the salt accumulation rate exceeds a first threshold, the current plant species can be adjusted based on a pre-established plant species screening library.

[0008] Optionally, it also includes: collecting historical photovoltaic parameters of the vertical photovoltaic array and historical soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; performing feature screening on the historical photovoltaic parameters and historical soil monitoring indicators to obtain target photovoltaic parameters and target soil monitoring indicators; obtaining simulation results of salt transport in each monitoring unit of the vertical photovoltaic array based on the water-salt transport model; and training the soil salinity prediction model based on the target photovoltaic parameters, target soil monitoring indicators and simulation results to obtain the trained soil salinity prediction model.

[0009] Optionally, monitoring units are set up in the front area, under area and between areas of the vertical photovoltaic array; each monitoring unit has multiple monitoring points set up along the soil layers.

[0010] Optionally, the area in front of the slab is irrigated through underground drainage pipes; the area under the slab is irrigated by drip irrigation, with a frequency of once every first preset number of days; the area between the slabs is irrigated by pulse drip irrigation, with a frequency of once every second preset number of days; wherein the first preset number of days is greater than the second preset number of days.

[0011] Secondly, the present invention provides a soil salinity control device under a vertical photovoltaic array, comprising: a parameter acquisition module for acquiring photovoltaic parameters of the vertical photovoltaic array and soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; a salinity prediction module for inputting the photovoltaic parameters and soil monitoring indicators into a pre-trained soil salinity prediction model to obtain salinity prediction results for each monitoring unit of the vertical photovoltaic array; and a control module for determining the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results.

[0012] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of the method provided in any of the first aspects above.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the steps of the method provided in any of the first aspects above.

[0014] This invention brings the following beneficial effects: The soil salinity control method and apparatus under a vertical photovoltaic array provided by this invention first collects photovoltaic parameters of the vertical photovoltaic array and soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; then, the photovoltaic parameters and soil monitoring indicators are input into a pre-trained soil salinity prediction model to obtain the salinity prediction results of each monitoring unit of the vertical photovoltaic array; finally, the corresponding irrigation mode and plant varieties for each monitoring unit are determined based on the salinity prediction results. In the above method, monitoring units are set based on the asymmetric shading characteristics of the vertical photovoltaic array, and the collected soil monitoring indicators and photovoltaic parameters of each monitoring unit are used to obtain the salinity prediction results of each monitoring unit based on the pre-trained soil salinity prediction model. Finally, the irrigation mode and plant varieties of each area are adjusted according to the salinity prediction results, thereby improving the accuracy of salinity prediction in the vertical photovoltaic array area, as well as the adaptability of brackish water irrigation and salt-tolerant plant configuration, and thus improving the ecological restoration efficiency and land use efficiency of the vertical photovoltaic power station.

[0015] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 A flowchart of a soil salinity regulation method under a vertical photovoltaic array provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a soil salinity regulation device under a vertical photovoltaic array provided in an embodiment of the present invention; Figure 3A flowchart of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Currently, existing technologies are unable to accurately predict the salinity distribution patterns of vertical photovoltaic arrays, which makes it impossible for them to be adapted to brackish water irrigation and salt-tolerant plant configurations for vertical photovoltaic arrays. This results in low ecological restoration efficiency and land use efficiency of vertical photovoltaic power stations.

[0021] Based on this, the present invention provides a method and apparatus for regulating soil salinity under a vertical photovoltaic array, which can improve the ecological restoration efficiency and land use efficiency of vertical photovoltaic power stations.

[0022] To facilitate understanding of this embodiment, a method for controlling soil salinity under a vertical photovoltaic array, as disclosed in this embodiment of the invention, will first be described in detail. This method can be executed by electronic devices, such as smartphones, computers, and tablets. See also... Figure 1 The flowchart shown illustrates a method for regulating soil salinity under a vertical photovoltaic array, indicating that the method mainly includes the following steps S101 to S103: Step S101: Collect photovoltaic parameters of the vertical photovoltaic array and soil monitoring indicators of each monitoring unit of the vertical photovoltaic array.

[0023] In one embodiment, monitoring units are respectively set in the front area, under area and between areas of the vertical photovoltaic array; each monitoring unit has multiple monitoring points set along the soil layers.

[0024] Specifically, monitoring points are set up according to the principle of horizontal zoning + vertical layering. Monitoring units are set up in the front area of ​​the vertical photovoltaic array (0-2m on the windward side of the module), the under-panel area (directly below the module), and the inter-panel area (midpoint of the distance between adjacent modules). Each monitoring unit has monitoring points along the 0-10cm (topsoil layer), 10-30cm (subsoil layer), and 30-50cm (subsoil layer). At the same time, a control monitoring point is set up 100m outside the array to ensure data comparability.

[0025] In practice, soil sensors are used to monitor soil indicators in real time, including but not limited to: soil electrical conductivity (EC), temperature, moisture content, atmospheric temperature and humidity, wind speed, and precipitation; simultaneously, soil samples are collected in the middle of each month to detect Na+.+ Ca² + Mg² + Record isochloride ion content and pH value, and increase monitoring frequency (once every 3 days) before and after brackish water irrigation. Record photovoltaic parameters of the vertical photovoltaic array, including but not limited to: structural parameters such as module height, spacing, tilt angle, and light transmittance, as well as light environment data such as photovoltaic panel shading duration and radiation intensity.

[0026] Step S102: Input the photovoltaic parameters and soil monitoring indicators into the pre-trained soil salinity prediction model to obtain the salinity prediction results of each monitoring unit of the vertical photovoltaic array.

[0027] In one implementation, the collected photovoltaic parameters and soil monitoring indicators are input into a pre-trained soil salinity prediction model, and the salinity prediction results are output to each monitoring unit of the vertical photovoltaic array.

[0028] Step S103: Determine the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results.

[0029] In one implementation, the salinity prediction results include: salinity content and salinity accumulation rate over a preset time period. Based on the salinity content output by the soil salinity prediction model, the soil salinity risk of each monitoring unit is divided into three levels: low risk, medium risk, and high risk. The corresponding irrigation mode is determined according to the risk level. At the same time, the plant varieties to be planted in each monitoring unit are determined based on the salinity accumulation rate output by the soil salinity prediction model.

[0030] The soil salinity control method under the vertical photovoltaic array provided in this embodiment of the invention sets up monitoring units based on the asymmetric shading characteristics of the vertical photovoltaic array, and uses the collected soil monitoring indicators and photovoltaic parameters of each monitoring unit to obtain the salinity prediction results of each monitoring unit based on a pre-trained soil salinity prediction model. Finally, the irrigation mode and plant varieties of each area are adjusted according to the salinity prediction results, thereby improving the accuracy of salinity prediction in the vertical photovoltaic array area, as well as the adaptability of brackish water irrigation and salt-tolerant plant configuration, and thus improving the ecological restoration efficiency and land use efficiency of the vertical photovoltaic power station.

[0031] In one implementation, for the aforementioned step S103, i.e., when determining the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results, the following methods may be adopted, including but not limited to: (1) Soil salinity maintenance under brackish water irrigation: Based on the salinity content, the soil salinity risk level of each monitoring unit of the vertical photovoltaic array is determined, and the irrigation mode of each monitoring unit is determined based on the soil salinity risk level.

[0032] In practical implementation, soil salinity risk levels are categorized into low risk, medium risk, and high risk. Based on the salinity content output by the soil salinity prediction model, the soil salinity risk of each monitoring unit is divided into three levels: low risk (EC < 4 dS / m), medium risk (4 dS / m ≤ EC < 8 dS / m), and high risk (EC ≥ 8 dS / m).

[0033] If the soil salinity risk level is low, the original brackish water is used for irrigation; if the soil salinity risk level is medium, the original brackish water is mixed with desalinated water driven by photovoltaic power generation in a preset ratio (e.g., 1:1) before irrigation; if the soil salinity risk level is high, desalinated water (salt content ≤0.3g / L) is used for irrigation, and the amount of leaching water is increased by 20%-30%.

[0034] In this embodiment of the invention, different irrigation methods can be used for different areas of the vertical photovoltaic array, namely: the area in front of the panel is irrigated through drainage pipes to promptly remove leaching salts; the area under the panel is irrigated by drip irrigation, with a frequency of once every first preset number of days, for example, once every 7 days, to reduce salt accumulation caused by water evaporation; the area between the panels is irrigated by pulse drip irrigation, with a frequency of once every second preset number of days, for example, once every 3 days, for 15 minutes each time, to enhance the downward migration of salts; wherein, the first preset number of days is greater than the second preset number of days.

[0035] In addition, for medium- and high-risk areas, organic materials (a mixture of decomposed straw and sheep manure, applied at a rate of 2000 kg / mu) and gypsum conditioner (applied at a rate of 500 kg / mu) can be applied to improve soil structure and promote salt leaching; in inter-particle areas, additional biostimulants (containing humic acid substances) can be applied to alleviate the stress of salt ions on plant roots.

[0036] (2) Targeted configuration of salt-tolerant plants: Based on the rate of salt accumulation, determine the plant species for each monitoring unit.

[0037] In practice, if the rate of salt accumulation exceeds the first threshold, the current plant variety will be adjusted based on a pre-established plant variety screening library.

[0038] Specifically, plant varieties with suitable salt tolerance, shade tolerance, and drought tolerance are screened to establish a four-level plant variety screening library: Level 1 screening library (strong salt tolerance + strong shade tolerance, EC tolerance value ≥8dS / m) includes: tiger pea and Suaeda salsa; Level 2 screening library (medium salt tolerance + medium shade tolerance, EC tolerance value 4-8dS / m) includes: winter wheat and rapeseed; Level 3 screening library (medium salt tolerance + light-loving, EC tolerance value 4-8dS / m) includes: Reed and sweet sorghum; Level 4 strong library (weak salt tolerance + shade tolerance, EC tolerance value <4dS / m) includes: alfalfa and ryegrass.

[0039] Under-the-board area (shading rate ≥70%, low to medium salinity): Plants from the primary screening library + the secondary screening library are configured, and a mixed sowing pattern of tiger nuts and alfalfa is adopted. Tiger nuts have a well-developed root system to fix the soil, and alfalfa improves soil fertility, which is suitable for shading and low salinity environment.

[0040] Intercropping area (shading rate 30%-50%, medium to high salinity): Plants are selected from a primary screening library and a tertiary screening library. The intercropping pattern of Suaeda salsa and Phragmites australis is adopted. Suaeda salsa reduces surface salinity, while Phragmites australis absorbs deep salinity through its deep root system, which is suitable for both sufficient light and high salinity.

[0041] Front area (shading rate and salinity): Plants from the secondary screening library are selected, with winter wheat or rapeseed planted alone, which are suitable for strong light and medium salinity environment.

[0042] In this embodiment of the invention, the plant configuration is adjusted every 30 days based on the prediction results of the salinity prediction model. For example, if the salinity accumulation rate in a certain area exceeds 0.5 dS / m If the salinity of a region drops to a low-risk range for 60 consecutive days, the plants in that region can be replaced with plant varieties from a lower-level screening library, thereby improving economic benefits.

[0043] In a real-time manner, the training process of the aforementioned soil salinity prediction model includes: first, collecting historical photovoltaic parameters of the vertical photovoltaic array and historical soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; then, performing feature filtering on the historical photovoltaic parameters and historical soil monitoring indicators to obtain target photovoltaic parameters and target soil monitoring indicators; next, obtaining simulation results of salt transport in each monitoring unit of the vertical photovoltaic array based on a water-salt transport model; finally, training the soil salinity prediction model based on the target photovoltaic parameters, target soil monitoring indicators, and simulation results to obtain a trained soil salinity prediction model.

[0044] In practice, a hybrid embedded feature selection strategy is used to screen the collected historical monitoring data (containing at least one complete dry and rainy season cycle) to obtain key variables, namely target photovoltaic parameters and target soil monitoring indicators, including but not limited to: soil temperature, moisture content, electrical conductivity, and salt ion content (Na₂O₃). + (Mainly, photovoltaic shading rate, wind speed, brackish water irrigation volume and salinity, etc.)

[0045] Specifically, the variance of each variable is calculated, and a threshold (e.g., 0.01) is set. Variables with variances below this threshold are directly eliminated. The correlation coefficient matrix between all pairs of variables is also calculated. For each pair of highly correlated variables (e.g., correlation coefficient greater than 0.95), only one is retained, and the other is eliminated. Then, a model with L1 regularization (e.g., Lasso regression) is trained using the filtered feature data. During training, the model automatically adjusts the coefficients of each feature. After training, the coefficients of each feature in the model are examined, and all features with non-zero coefficients are selected as key variables for model selection.

[0046] Furthermore, an ensemble learning model based on random forest was constructed, integrating simulation results from the Hydrous-1D water-salt transport model to select key variables and train the model. A dynamic weighting strategy was then used to optimize prediction accuracy, resulting in a well-trained soil salinity prediction model. The model outputs predictions of salinity content (EC values) and salt accumulation rates for different regions and soil layers (e.g., short-term 7-day salt accumulation rate, medium-term 30-day salt accumulation rate, and long-term 180-day salt accumulation rate).

[0047] In practical implementation, the Hydrus-1D water-salt transport model simulation process includes: based on the geological data of the vertical photovoltaic array area, dividing the soil vertically into several layers with different hydraulic properties, and dividing the vertical profile into computational grids; using van... The Genuchten-Mualem model is used to describe the soil moisture characteristic curve and hydraulic conductivity function. Key parameters include residual moisture content, saturated moisture content, shape parameters, and saturated moisture content. The model determines the transport characteristics of salt (EC value) in the soil, mainly including longitudinal dispersion, used to describe the diffusion and mechanical dispersion of solutes in pore water. Boundary and initial conditions are defined. The upper boundary is the atmospheric boundary, inputting meteorological data (rainfall, evaporation) and irrigation regime, setting surface runoff and evaporation flux to simulate moisture exchange at the atmosphere-soil interface. The lower boundary is the groundwater boundary, set as a free drainage or variable head boundary to simulate the impact of groundwater level fluctuations on water and salt transport in shallow soils. The initial moisture content and initial salt concentration (EC value) of each soil layer are set at the start of the simulation. Hydrus-1D models are established for different regions (e.g., different soil textures, different groundwater depths). Long-term historical meteorological data are input into Hydrus-1D, and the distribution of moisture content and salt concentration in each soil layer over time is output.

[0048] Furthermore, the simulation results of Hydrus-1D were aligned with historical monitoring data to construct a training dataset. The random forest regression model was then trained using this dataset, and the model learned the nonlinear mapping relationship between input features and output target (EC value).

[0049] In this embodiment of the invention, prediction accuracy is optimized through a dynamic weighting strategy. Specifically, the weight W is defined as the environmental state function f(S), where S represents state variables (such as soil saturation, rainfall intensity, etc.). During periods of drought and low rainfall, water movement is mainly driven by evaporation, and salt accumulates on the surface. In this case, the description of physical processes by Hydrorus-1D (such as capillary upwelling) may be more accurate, and the weight of Hydrorus-1D can be appropriately increased, or the simulated values ​​of Hydrorus-1D can be used as strong feature inputs for the random forest. During periods of heavy rainfall, unsaturated flow and preferred flow dominate. If the random forest model can capture the nonlinear relationship between historical rainfall and leaching, the weight of the random forest can be increased to correct the errors caused by parameter uncertainties in the physical model. Using historical monitoring data as the ground truth, the prediction error under different weight combinations is calculated. By using a sliding time window, the dynamic weight function that minimizes the prediction error is found.

[0050] The soil salinity control method under vertical photovoltaic arrays provided in this invention couples vertical photovoltaic structural parameters (shading rate, module spacing) with microclimate factors and brackish water irrigation parameters to establish a random forest-Hydrus-1D coupled prediction model. This solves the problem that existing models are difficult to adapt to asymmetric shading of vertical photovoltaics, thus improving prediction accuracy. A directional configuration strategy of salinity grading and microhabitat adaptation is adopted to establish a four-level salt-tolerant plant screening library, achieving precise adaptation to different photovoltaic areas. A dynamic adjustment mechanism is introduced to adapt to dynamic changes in salinity accumulation, improving plant survival rate and yield. A tiered irrigation + regionally differentiated salt management scheme is employed, utilizing vertical photovoltaic panel power generation to drive desalination water production without additional energy consumption, reducing desalination equipment costs. Combined with soil conditioners and optimized irrigation methods, efficient salinity control is achieved. In summary, this invention improves the problem of soil salinity accumulation caused by brackish water irrigation under vertical photovoltaic arrays, significantly improving the land use efficiency and ecological restoration effect of photovoltaic power stations.

[0051] This invention also provides a method for determining monitoring units for a vertical photovoltaic array. A simulation model of the vertical photovoltaic array region is established based on environmental parameters and array structure, and the optimal number and location of monitoring units are intelligently recommended based on the simulation model. Establishing the simulation model of the vertical photovoltaic array region includes: (1) Construct a three-dimensional periodic geometric computational domain.

[0052] Specifically, obtain the array parameters of the vertical photovoltaic array, including but not limited to: module height H, ground clearance H. gap Installation tilt angle θ(Vertical photovoltaics are typically 90° or dual-axis tracking) and the spacing L between adjacent modules, and calculate the domain boundary: X-axis (span direction): take one panel spacing L; Y-axis (height direction): from the ground surface (y=0) to the top of the atmospheric boundary layer (y=3H) 5H); Z-axis (wind direction depth): 2H is taken in the front area of ​​the plate (to capture the influence of the wake), and 3H is taken in the rear area of ​​the plate.

[0053] Meanwhile, the functional subdomains are meshed: the mesh in front of the panel is fined (dx<0.1m) to capture boundary layer peeling; the area under the panel: the projection area of ​​the photovoltaic panel, focusing on shading and drip lines; the area between the panels: the central area between two adjacent panels, serving as a background reference.

[0054] (2) Microclimate flow field and dust deposition modeling.

[0055] Specifically, the CFD wind field model (wind speed v, wind direction α) and the radiative transfer model (solar altitude angle β, reflectivity ρ) are coupled to calculate the dust deposition rate D(x,y,z,t) in each region.

[0056] The solar altitude angle and azimuth angle are calculated based on the latitude, longitude, and date of the area where the vertical photovoltaic array is located. Then, ray tracing is used to calculate the projected area of ​​the photovoltaic panel on the Earth's surface at each moment. For any point (x, y) on the Earth's surface, its net radiation... Rn Determined by the following formula: Rn ( x , y , t )=(1 α ) Sin δsun ( x , y , t )+ Lin Lout in, δsun The solar radiation coefficient, in the sub-plate region, changes dynamically over time (fluctuating between 0 and 1). Will Rn Substituting the heat source term into the soil heat conduction equation generates an unsteady temperature field T(x,y,z,t).

[0057] (3) Construction of hydrothermal salt transport field.

[0058] Specifically, based on the Richards equation and the heat conduction equation, a photovoltaic panel shading coefficient γ(x,y,z) is introduced (γ=0.3-0.5 in the under-panel region, γ=0.8-1.0 in the in front / between regions) to simulate salt migration during rainfall infiltration and evaporation: ( KC ) / t = ( θD C ) ( qC ) Ssalt in, K Soil moisture content; C This refers to the salt concentration in the soil solution. D The hydrodynamic dispersion coefficient, Ssalt The salt concentrations are source and sink factors, with the dissolution of dust accumulated in the area in front of the plate being a significant source of salt (source factor); if there is vegetation, root absorption of salt should be considered.

[0059] Structural interference factors include: Front region of the plate: windward side vortex intensity coefficient ω1=f(v,α,H / L); Under the board area: Shading-dripping synergistic effect coefficient ω2=γ·δ (δ: dripping unevenness); Interplate region: wake interference coefficient ω3=g(v,α,L / H).

[0060] Finally, a three-dimensional spatiotemporal salt distribution field EC(x,y,z,t) is generated, marking high-variability regions (ΔEC / Δt>threshold) and stable regions.

[0061] Furthermore, based on the simulation model, the optimal number and location of monitoring units are intelligently recommended, including: (1) Obtain environmental data, structural data, and constraints for the vertical photovoltaic array to generate a basic simulation model. Environmental data includes: historical weather data (wind speed, rainfall, evaporation), and initial soil EC / moisture content / temperature profiles; structural data includes: module height H, installation tilt angle (vertical photovoltaics are typically 90° or dual-axis tracking), spacing L between adjacent modules, and module reflectivity. ρ Constraints include: the maximum number of monitoring units N. max Minimum coverage rate η in a single area min .

[0062] (2) Run the aforementioned multiphysics model, output typical daily / monthly salinity distribution cloud maps, and extract characteristic parameters of each region, including: Front area: dust accumulation rate D front Wind erosion intensity E; Under-slab area: Shading duration T shade Salt enrichment coefficient of dripping water κ Interplate zone: Uniformity of water and heat exchange σ .

[0063] (3) Discretize the monitoring area into a grid point set. P ={ p i}, extract feature vectors for each point F i =[EC i , EC i ,T i ,θ i D i ]( EC: Salinity gradient).

[0064] (4) An improved DBSCAN algorithm is used for adaptive weighted clustering, and the core point of each cluster is selected as a candidate monitoring location. Distance metric is used to introduce structural weights:

[0065] Among them, weight Adjustments will be made dynamically based on regional conditions: Front Area: w D =0.4 (dust-dominated); Underplate area: w κ =0.5 (drip-dominant); Interplate area: w σ =0.3 (Uniformity dominates).

[0066] (5) Based on the candidate point monitoring data, Kriging interpolation is used to reconstruct the full-field salinity distribution EC'(x,y,z), and the relative error between it and the simulated true value EC is calculated. If the relative error is greater than the error threshold (e.g., 15%) or the regional coverage is less than the minimum coverage η of a single region, the error is considered. min If so, then execute: increase the number of points along the wind direction gradient in the front area of ​​the board (Δx≤0.5m).

[0067] Finally, the number of output monitoring units is allocated (e.g., front plate area: bottom plate area: inter-plate area ≈ 3:2:2), the set of location coordinates, and the priority labels (P1 (high-variability core area) / P2 (transition area) / P3 (stable area)).

[0068] The method for generating the monitoring unit provided in this embodiment of the invention integrates multiple physical processes such as wind, light, water, heat, and salt, quantifies the synergistic effects of dust accumulation, shading, and dripping water on salinity, and introduces array structure weights (dust accumulation / dripping water / wake coefficient) to deeply bind the layout of monitoring points with physical mechanisms; through virtual reconstruction error inversion optimization, it ensures that there are no monitoring blind spots in each area (especially the wind erosion zone in front of the plate and the dripping zone under the plate).

[0069] Regarding the soil salinity control method under a vertical photovoltaic array provided in the foregoing embodiments, this invention also provides a soil salinity control device under a vertical photovoltaic array, see [link to relevant documentation]. Figure 2 The schematic diagram shown illustrates the structure of a soil salinity regulation device under a vertical photovoltaic array, indicating that the device mainly includes the following parts: The parameter acquisition module 201 is used to acquire the photovoltaic parameters of the vertical photovoltaic array and the soil monitoring indicators of each monitoring unit of the vertical photovoltaic array.

[0070] The salinity prediction module 202 is used to input photovoltaic parameters and soil monitoring indicators into a pre-trained soil salinity prediction model to obtain the salinity prediction results of each monitoring unit of the vertical photovoltaic array.

[0071] The regulation module 203 is used to determine the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results.

[0072] The soil salinity control device under the vertical photovoltaic array provided in this embodiment of the invention sets up monitoring units based on the asymmetric shading characteristics of the vertical photovoltaic array, and uses the collected soil monitoring indicators and photovoltaic parameters of each monitoring unit to obtain the salinity prediction results of each monitoring unit based on a pre-trained soil salinity prediction model. Finally, the irrigation mode and plant varieties of each area are adjusted according to the salinity prediction results, thereby improving the accuracy of salinity prediction in the vertical photovoltaic array area, as well as the adaptability of brackish water irrigation and salt-tolerant plant configuration, and thus improving the ecological restoration efficiency and land use efficiency of the vertical photovoltaic power station.

[0073] In one embodiment, the salt prediction results include: salt content and salt accumulation rate within a preset time period; the aforementioned control module 203 is specifically used to: determine the soil salinity risk level of each monitoring unit of the vertical photovoltaic array based on the salt content, and determine the irrigation mode of each monitoring unit based on the soil salinity risk level; and determine the plant species of each monitoring unit based on the salt accumulation rate.

[0074] In one embodiment, the soil salinity risk level includes: low risk, medium risk, and high risk; the aforementioned control module 203 is further used to: if the soil salinity risk level is low risk, then use the original brackish water for irrigation; if the soil salinity risk level is medium risk, then mix the original brackish water with desalinated water driven by photovoltaic power generation according to a preset ratio for irrigation; if the soil salinity risk level is high risk, then use desalinated water for irrigation.

[0075] In one embodiment, the above-mentioned regulation module 203 is further used to: if the salt accumulation rate exceeds a first threshold, adjust the current plant variety based on a pre-established plant variety screening library.

[0076] In one embodiment, the above-mentioned device further includes: a model training module, used for: collecting historical photovoltaic parameters of the vertical photovoltaic array and historical soil monitoring indicators of each monitoring unit of the vertical photovoltaic array; performing feature screening on the historical photovoltaic parameters and historical soil monitoring indicators to obtain target photovoltaic parameters and target soil monitoring indicators; obtaining simulation results of salt transport in each monitoring unit of the vertical photovoltaic array based on a water-salt transport model; and training the soil salinity prediction model based on the target photovoltaic parameters, target soil monitoring indicators and simulation results to obtain a trained soil salinity prediction model.

[0077] In one embodiment, the monitoring units are respectively set in the front area, under area and between areas of the vertical photovoltaic array; each monitoring unit has multiple monitoring points set along the soil layers.

[0078] In one embodiment, the area in front of the slab is irrigated by a drainage pipe; the area under the slab is irrigated by drip irrigation, with the drip irrigation frequency being once every first preset number of days; the area between the slabs is irrigated by pulse drip irrigation, with the pulse drip irrigation frequency being once every second preset number of days; wherein, the first preset number of days is greater than the second preset number of days.

[0079] It should be noted that the device provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment. The specific numerical values ​​provided in this embodiment are merely exemplary and are not intended to limit the scope of the invention.

[0080] This invention also provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program, when run by the processor, executes the method described in any of the above embodiments.

[0081] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 30, a memory 31, a bus 32 and a communication interface 33. The processor 30, the communication interface 33 and the memory 31 are connected through the bus 32. The processor 30 is used to execute executable modules, such as computer programs, stored in the memory 31.

[0082] The memory 31 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 33 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0083] Bus 32 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0084] The memory 31 is used to store programs. After receiving an execution instruction, the processor 30 executes the program. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 30 or implemented by the processor 30.

[0085] Processor 30 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 30 or by instructions in software form. Processor 30 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 31. The processor 30 reads the information in memory 31 and, in conjunction with its hardware, completes the steps of the above method.

[0086] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0087] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for regulating soil salinity under a vertical photovoltaic array, characterized in that, include: The photovoltaic parameters of the vertical photovoltaic array and the soil monitoring indicators of each monitoring unit of the vertical photovoltaic array are collected. The photovoltaic parameters and the soil monitoring indicators are input into a pre-trained soil salinity prediction model to obtain the salinity prediction results of each monitoring unit of the vertical photovoltaic array. Based on the salinity prediction results, the corresponding irrigation mode and plant varieties for each monitoring unit are determined.

2. The method according to claim 1, characterized in that, The salt content prediction results include: salt content and salt accumulation rate within a preset time period; Based on the salinity prediction results, the corresponding irrigation patterns and plant varieties for each monitoring unit are determined, including: Based on the salt content, the soil salinity risk level of each monitoring unit of the vertical photovoltaic array is determined, and the irrigation mode of each monitoring unit is determined based on the soil salinity risk level. Based on the salt accumulation rate, the plant species of each monitoring unit are determined.

3. The method according to claim 2, characterized in that, The soil salinity risk levels are categorized as low, medium, and high; the irrigation patterns for each monitoring unit are determined based on these soil salinity risk levels, including: If the soil salinity risk level is low, then the original brackish water shall be used for irrigation. If the soil salinity risk level is medium risk, the original brackish water and the desalinated water driven by photovoltaic power generation will be mixed in a preset ratio and then used for irrigation. If the soil salinity risk level is high, then desalinated water shall be used for irrigation.

4. The method according to claim 3, characterized in that, Based on the salt accumulation rate, the plant species for each monitoring unit are determined, including: If the salt accumulation rate exceeds a first threshold, the plant varieties currently planted in each monitoring unit are adjusted based on a pre-established plant variety screening library and the screening library level corresponding to the plant varieties currently planted in each monitoring unit; wherein, the plant variety screening library is established based on the salt tolerance, shade tolerance and drought tolerance of plant varieties, and includes multiple levels.

5. The method according to claim 1, characterized in that, Also includes: Historical photovoltaic parameters of the vertical photovoltaic array and historical soil monitoring indicators of each monitoring unit of the vertical photovoltaic array were collected. By performing feature screening on the historical photovoltaic parameters and the historical soil monitoring indicators, target photovoltaic parameters and target soil monitoring indicators are obtained; Obtain simulation results of salt transport in each monitoring unit of the vertical photovoltaic array based on a water-salt transport model; Based on the target photovoltaic parameters, the target soil monitoring indicators, and the simulation results, the soil salinity prediction model is trained to obtain a trained soil salinity prediction model.

6. The method according to claim 1, characterized in that, The monitoring units are respectively set in the front area, under area and between areas of the vertical photovoltaic array; each monitoring unit has multiple monitoring points set along the soil layers.

7. The method according to claim 6, characterized in that, The area in front of the slab is irrigated through a drainage pipe; the area under the slab is irrigated by drip irrigation, with the drip irrigation frequency being once every first preset number of days; the area between the slabs is irrigated by pulse drip irrigation, with the pulse drip irrigation frequency being once every second preset number of days; wherein, the first preset number of days is greater than the second preset number of days.

8. A soil salinity regulation device under a vertical photovoltaic array, characterized in that, include: The parameter acquisition module is used to acquire the photovoltaic parameters of the vertical photovoltaic array and the soil monitoring indicators of each monitoring unit of the vertical photovoltaic array. The salinity prediction module is used to input the photovoltaic parameters and the soil monitoring indicators into a pre-trained soil salinity prediction model to obtain the salinity prediction results of each monitoring unit of the vertical photovoltaic array. The control module is used to determine the corresponding irrigation mode and plant variety for each monitoring unit based on the salinity prediction results.

9. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the steps of the method described in any one of claims 1 to 7.

Images