Sensor layout optimization method for photovoltaic agricultural inter-board and under-board space environment monitoring

Abstract

The invention relates to a sensor layout optimization method for photovoltaic agricultural inter-board and under-board space environment monitoring, and the method comprises the steps: S1, determining a sensor layout principle which comprises representativeness, coverage, redundancy and economy; s2, dividing the target monitoring area into a plurality of grids, and preliminarily determining the arrangement positions of sensors in the target monitoring area; s3, establishing a target function; s4, setting constraint conditions; and S5, coding the sensor layout position as a chromosome and coding each grid as a gene, determining the optimal solution of the target function according to the genetic algorithm, and determining the number of grids divided in the target monitoring area and the optimal layout position of the sensor in the target monitoring area according to the optimal target function. The beneficial effects are that the optimization method can solve the problems of insufficient representativeness and accuracy in the existing sensor layout method, enables the layout of the sensor in the photovoltaic agricultural environment to be more representative, and improves the precision and efficiency of environment monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural environmental monitoring and optimization, and in particular to a sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels. Background Art

[0002] Photovoltaic agriculture combines photovoltaic power generation with agricultural production, and achieves sustainable development of agricultural production through scientific management and advanced technology. However, due to the presence of photovoltaic panels, parameters such as light, temperature, and humidity in the agricultural environment will be affected to a certain extent. Therefore, it is necessary to accurately monitor the photovoltaic agricultural environment, and the reasonable layout of sensors is the key to achieving accurate monitoring. The existing sensor layout methods are mostly simple uniform layouts, which make it difficult to fully consider the environmental differences under and between photovoltaic panels, resulting in insufficient representativeness and accuracy of monitoring data. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels, so as to overcome the deficiencies in the above-mentioned prior art.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: A sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels, comprising the following steps:

[0005] S1. Establish sensor deployment principles, including representativeness, coverage, redundancy, and economy;

[0006] S2, dividing the target monitoring area into multiple grids, and preliminarily determining the sensor deployment locations within the target monitoring area;

[0007] S3, establish the objective function;

[0008] S4. Set constraints;

[0009] S5. Encode the sensor layout position as a chromosome and encode each grid as a gene, and determine the optimal solution of the objective function based on the genetic algorithm. Then, based on the optimal objective function, the number of grids divided into the target monitoring area and the optimal layout position of the sensors in the target monitoring area can be determined.

[0010] Based on the above technical solution, the present invention can also be improved as follows.

[0011] Further, the representativeness is as follows: the sensor layout includes the under-panel area and the inter-panel area, and the monitored environmental data should represent the diversity of photovoltaic agricultural environments;

[0012] Coverage: Based on the monitoring range of a single sensor, the total monitoring range formed by all deployed sensors should cover the entire target monitoring area;

[0013] Redundancy: the redundancy of the deployed sensors;

[0014] Economical: Reduce the number of sensors while meeting monitoring requirements.

[0015] Furthermore, the distribution of sensors in the under-board area follows the following principles: the density of sensors is low, but they should cover the entire under-board area;

[0016] The principle followed by the distribution of sensors in the area between photovoltaic panels is: high sensor density.

[0017] Furthermore, the grid size is determined according to the arrangement of PV panels and the monitoring range of sensors.

[0018] Furthermore, the objective function is defined as follows:

[0019] F=α×C coverage +β×C cost +γ×C redundancy

[0020] Among them, C coverage Indicates the coverage of monitoring data, C cost represents the layout cost, C redundancy represents redundancy, α, β, γ are weight coefficients;

[0021]

[0022] Among them, C i Indicates the coverage of the i-th grid sensor. If there is sensor coverage, then C i =1, otherwise C i =0, N represents the number of grids into which the monitoring area is divided;

[0023]

[0024] Where: x i Indicates whether the i-th grid is equipped with sensors. If so, x i =1, otherwise x i =0; cost i represents the cost of deploying sensors in the i-th grid, and N represents the number of grids divided into the monitoring area;

[0025]

[0026] Where: r i Represents the redundancy of the i-th grid. If the grid is covered by multiple sensors, then r i is the redundancy, that is, the number of redundant sensors, otherwise r i =0, N represents the number of grids into which the monitoring area is divided.

[0027] Furthermore, the constraints set are: at least one sensor is deployed in each grid; the coverage of the sensor should take into account the environmental differences under and between photovoltaic panels; and the deployment cost does not exceed the preset budget.

[0028] Furthermore, the method for determining the optimal solution of the objective function by genetic algorithm is as follows:

[0029] S61, encoding: Encode the sensor deployment position as a chromosome, using binary encoding. Assume that the monitoring area is divided into N grids, and each grid is encoded as a gene with a value of 0 or 1, where 0 means no sensor is deployed and 1 means a sensor is deployed;

[0030] S62, initial population: randomly generate an initial population with a population size of P;

[0031] S63, fitness value: Calculate the fitness value f of each chromosome according to the objective function:

[0032]

[0033] S64, selection: Roulette selection method is used to select chromosomes to enter the next generation according to fitness values;

[0034] S65, Crossover: Use the single-point crossover method to perform a crossover operation on the selected chromosomes to generate new offspring;

[0035] S66, mutation: mutation operation is performed on the chromosome after crossover to randomly change certain genes in the chromosome;

[0036] S67, Update population: replace the old population with the generated offspring and enter the next generation of iteration;

[0037] S68, termination condition: When the preset number of iterations is reached or the fitness value reaches the preset standard, the algorithm terminates and outputs the optimal solution, that is, the optimal solution of the objective function is determined.

[0038] The beneficial effect of the present invention is that the optimization method can solve the problems of insufficient representativeness and accuracy in existing sensor deployment methods, make the deployment of sensors in photovoltaic agricultural environments more representative, and improve the accuracy and efficiency of environmental monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of the sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels in the present invention;

[0040] Figure 2 This is a flow chart for determining the optimal solution of the objective function according to the genetic algorithm in the present invention. DETAILED DESCRIPTION

[0041] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0042] Example 1

[0043] like Figure 1 As shown, a sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels includes the following steps:

[0044] S1. Establish sensor deployment principles, including representativeness, coverage, redundancy, and economy;

[0045] S2. Divide the target monitoring area into multiple grids, and preliminarily determine the sensor deployment locations within the target monitoring area based on the sensor deployment principle;

[0046] S3, establish the objective function;

[0047] S4. Set constraints;

[0048] S5. Encode the sensor layout position as a chromosome and encode each grid as a gene, and determine the optimal solution of the objective function based on the genetic algorithm. Then, based on the optimal objective function, the number of grids divided into the target monitoring area and the optimal layout position of the sensors in the target monitoring area can be determined.

[0049] Example 2

[0050] This embodiment is a further improvement on the basis of embodiment 1, and the details are as follows:

[0051] Representativeness is: the placement of sensors includes the area under the panels and the area between the panels, and the monitored environmental data should represent the diversity of the photovoltaic agricultural environment, especially the environmental differences under the photovoltaic panels and between the panels;

[0052] Coverage: Based on the monitoring range of a single sensor, the total monitoring range formed by all deployed sensors should cover the entire target monitoring area to avoid data blind spots;

[0053] Redundancy: The redundancy of the deployed sensors and appropriate redundant deployment to improve system reliability;

[0054] Economical: Reduce the number of sensors to reduce costs while meeting monitoring requirements.

[0055] Going further: the principle followed by the distribution of sensors in the under-panel area is: since there is less sunlight under the photovoltaic panels, the temperature and humidity changes are relatively small, so the density of sensors can be appropriately reduced, but it still needs to cover the entire under-panel area;

[0056] The principle followed by the distribution of sensors in the area between photovoltaic panels is: the light between photovoltaic panels is strong and the environmental data varies greatly, so the density of sensors should be relatively high to ensure the accuracy of monitoring data;

[0057] The grid size is determined according to the arrangement of photovoltaic panels and the monitoring range of sensors.

[0058] Example 3

[0059] This embodiment is a further improvement on the basis of Embodiment 1 or 2, and the details are as follows:

[0060] The objective function is established to maximize the representativeness and accuracy of the monitoring data and minimize the number of sensors and the deployment cost. The objective function is defined as follows:

[0061] F=α×C coverage +β×C cost +γ×C redundancy

[0062] Among them, C coverage Indicates the coverage of monitoring data. The larger the coverage, the higher the value. cost Represents the deployment cost. The fewer sensors there are, the lower the cost and the lower the value. C redundancy It represents redundancy. Appropriate redundancy helps to improve system reliability. α, β, and γ are weight coefficients used to adjust the relative importance of each part.

[0063]

[0064] Among them, C i Indicates the coverage of the i-th grid sensor. If there is sensor coverage, then C i =1, otherwise C i =0, N represents the number of grids into which the monitoring area is divided;

[0065]

[0066] Where: x i Indicates whether the i-th grid is equipped with sensors. If so, x i =1, otherwise x i =0; cost i represents the cost of deploying sensors in the i-th grid, and N represents the number of grids divided into the monitoring area;

[0067]

[0068] Where: r i Represents the redundancy of the i-th grid. If the grid is covered by multiple sensors, then r iis the redundancy, that is, the number of redundant sensors, otherwise r i =0, N represents the number of grids into which the monitoring area is divided.

[0069] Example 4

[0070] This embodiment is a further improvement on the basis of Embodiment 3, and the details are as follows:

[0071] The constraints set are: at least one sensor is deployed in each grid to ensure coverage; the coverage of the sensor should take into account the environmental differences under and between photovoltaic panels; and the deployment cost does not exceed the preset budget.

[0072] Example 5

[0073] like Figure 2 As shown, this embodiment is a further improvement on the basis of embodiment 4, and the details are as follows:

[0074] The method for genetic algorithm to determine the optimal solution of the objective function is as follows:

[0075] S61, encoding: Encode the sensor deployment position as a chromosome, using binary encoding. Assume that the monitoring area is divided into N grids, and each grid is encoded as a gene with a value of 0 or 1, where 0 means no sensor is deployed and 1 means a sensor is deployed;

[0076] S62, initial population: randomly generate an initial population with a population size of P;

[0077] S63, fitness value: Calculate the fitness value f of each chromosome according to the objective function:

[0078]

[0079] Among them, i represents the i-th chromosome;

[0080] S64, selection: Roulette selection method is used to select chromosomes to enter the next generation according to fitness values;

[0081] S65, crossover: Use the single-point crossover method to perform a crossover operation on the selected chromosomes, with a crossover probability of P c , generating new offspring;

[0082] S66, mutation: perform mutation operation on the chromosome after crossover, with a mutation probability of P m , to randomly change certain genes in chromosomes;

[0083] S67, Update population: replace the old population with the generated offspring and enter the next generation of iteration;

[0084] S68. Termination condition: When the preset number of iterations is reached or the fitness value reaches the preset standard, the algorithm terminates and outputs the optimal solution, that is, the optimal solution of the objective function is determined. The preset number of iterations is generally set according to computing resources and time constraints. If conditions permit, it can be set to 1000 times. Usually, the problem can converge to a good solution within hundreds to thousands of iterations. The preset standard can be set to 0~1, 1 represents a perfect solution, and a relatively high fitness value can be set according to actual conditions.

[0085] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels, characterized in that: The steps include: S1. Establish sensor deployment principles, including representativeness, coverage, redundancy, and economy; S2, dividing the target monitoring area into multiple grids, and preliminarily determining the sensor deployment locations within the target monitoring area; S3, establish the objective function; S4. Set constraints; S5. Encode the sensor layout position as a chromosome and encode each grid as a gene, and determine the optimal solution of the objective function based on the genetic algorithm. Then, based on the optimal objective function, the number of grids divided into the target monitoring area and the optimal layout position of the sensors in the target monitoring area can be determined.

2. The sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels according to claim 1 is characterized by: Representativeness is: the sensor layout includes the area under the panels and the area between the panels, and the monitored environmental data should represent the diversity of photovoltaic agricultural environments; Coverage: Based on the monitoring range of a single sensor, the total monitoring range formed by all deployed sensors should cover the entire target monitoring area; Redundancy: the redundancy of the deployed sensors; Economical: Reduce the number of sensors while meeting monitoring requirements.

3. A sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels according to claim 1 or 2, characterized in that: The principle followed by the distribution of sensors in the under-board area is: the sensor density is low, but it should cover the entire under-board area; The principle followed by the distribution of sensors in the area between photovoltaic panels is: high sensor density.

4. The sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels according to claim 1 is characterized by: The grid size is determined according to the arrangement of photovoltaic panels and the monitoring range of sensors.

5. A sensor layout optimization method for monitoring the space environment between photovoltaic agricultural panels and under the panels according to any one of claims 1 to 4, characterized in that: The objective function is defined as follows: F=α×C coverage +β×C cost +γ×C redundancy Among them, C coverage Indicates the coverage of monitoring data, C cost represents the layout cost, C redundancy represents redundancy, α, β, γ are weight coefficients; Among them, C i Indicates the coverage of the i-th grid sensor. If there is sensor coverage, then C i =1, otherwise C i =0, N represents the number of grids into which the monitoring area is divided; Where: x i Indicates whether the i-th grid is equipped with sensors. If so, x i =1, otherwise x i =0; cost i represents the cost of deploying sensors in the i-th grid, and N represents the number of grids divided into the monitoring area; Where: r i Represents the redundancy of the i-th grid. If the grid is covered by multiple sensors, then r i is the redundancy, that is, the number of redundant sensors, otherwise r i =0, N represents the number of grids into which the monitoring area is divided.

6. The method for optimizing sensor placement for monitoring the space environment between and under photovoltaic agricultural panels according to claim 5, characterized in that: The constraints set are: at least one sensor is deployed in each grid; the coverage of the sensor should take into account the environmental differences under and between photovoltaic panels; and the deployment cost does not exceed the preset budget.

7. The method for optimizing sensor layout for monitoring the space environment between and under photovoltaic agricultural panels according to claim 6, characterized in that: The method for genetic algorithm to determine the optimal solution of the objective function is as follows: S61, encoding: Encode the sensor deployment position as a chromosome, using binary encoding. Assume that the monitoring area is divided into N grids, and each grid is encoded as a gene with a value of 0 or 1, where 0 means no sensor is deployed and 1 means a sensor is deployed; S62, initial population: randomly generate an initial population with a population size of P; S63, fitness value: Calculate the fitness value f of each chromosome according to the objective function: S64, selection: Roulette selection method is used to select chromosomes to enter the next generation according to fitness values; S65, Crossover: Use the single-point crossover method to perform a crossover operation on the selected chromosomes to generate new offspring; S66, mutation: mutation operation is performed on the chromosome after crossover to randomly change certain genes in the chromosome; S67, Update population: replace the old population with the generated offspring and enter the next generation of iteration; S68, termination condition: When the preset number of iterations is reached or the fitness value reaches the preset standard, the algorithm terminates and outputs the optimal solution, that is, the optimal solution of the objective function is determined.

Images