A biomass collection, storage and transportation site selection optimization method

Abstract

The application discloses a biomass collection, storage and transportation site optimization method, and belongs to the technical field of biomass energy utilization and space optimization. The method comprises the following steps: acquiring biomass site data and trunk road information of a preset area, constructing a biomass distribution matrix of the preset area by means of geographical coordinates and density of the biomass site, setting weights of corresponding sites based on biomass density, clustering and reducing dimensions of the distribution matrix by means of the weights, and outputting a preset number of candidate site sets of biomass collection and storage stations; generating an address combination containing a preset number of optimal biomass collection and storage stations based on the candidate site sets of the biomass collection and storage stations; generating a candidate site set containing a preset number of biomass power plants along a line by means of the trunk road information; generating an address combination containing a preset number of optimal biomass power plants based on the candidate site set of the biomass power plants; and the method can accurately and economically determine an optimal address combination of biomass collection, storage and transportation in the preset area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biomass energy utilization and space optimization, and particularly relates to a biomass collection, storage, transportation and site selection optimization method. BACKGROUND

[0002] In large-scale utilization of biomass energy, the site selection of collection and storage stations and power plants is crucial to the cost of collection, storage and transportation, resource efficiency and engineering feasibility. However, the traditional method has been difficult to adapt to large-scale and high complexity requirements, and has significant limitations.

[0003] On the one hand, the traditional method has weak ability to process massive data. In the face of the characteristics of biomass resources "many points and wide surfaces" (such as 450,000 grid points), artificial experience or simple clustering method is inefficient and easy to be redundant, and also ignores the difference in resource density. The "equalization" treatment leads to clustering deviating from the enrichment area, increasing the invalid cost. On the other hand, the optimization algorithm is not well adapted to the actual constraints, and it is difficult to deal with the "multi-constraint, non-convex" problem of site selection. The road network constraint is not integrated, and the planning of collection and storage stations and power plants is disconnected, which cannot reduce the cost collaboratively. At the same time, the cost accounting dimension is not complete, only focusing on a single link and ignoring key parameters, resulting in large measurement deviation.

[0004] In summary, the existing technology cannot solve the core problems of data dimension reduction, resource quantification, multi-constraint optimization and multi-facility collaboration. Therefore, an intelligent site selection method that integrates geographic information and accurately quantifies resource value is needed to realize the unification of the minimum total cost of collection, storage and transportation and engineering practicability. SUMMARY

[0005] The purpose of the present application is to provide a biomass collection, storage and transportation site selection optimization method, which can accurately and economically determine the optimal combination of biomass collection, storage and transportation addresses in a preset area.

[0006] To solve the above technical problems, an embodiment of the present application provides a biomass collection, storage and transportation site selection optimization method, comprising the following steps:

[0007] Obtain all biomass site data and main road information in a preset area, and construct a biomass distribution matrix of the preset area based on the geographic coordinates and biomass density in all biomass site data;

[0008] Set the weight of the corresponding biomass site based on the biomass density, and perform clustering dimension reduction on the biomass distribution matrix of the preset area by the weight, to output a set of biomass collection and storage station candidate sites containing a preset number;

[0009] iteratively generating address combinations containing a preset number of biomass storage stations based on the set of candidate locations of the biomass storage stations; and screening the address combinations of the biomass storage stations, taking the distance cost from all biomass locations to the nearest biomass storage station and the construction cost of the biomass storage stations under the address combination of the biomass storage stations as screening targets to iteratively obtain an optimized address combination of the biomass storage stations;

[0010] iteratively generating address combinations containing a preset number of biomass power plants based on the set of candidate locations of the biomass power plants along the trunk road information; for each address combination of the biomass power plants, assigning each biomass storage station to the nearest biomass power plant, and calculating the distance cost from all biomass storage stations to the corresponding biomass power plant and the construction cost of the biomass power plants under the address combination of the biomass power plants; when the sum of the distance cost and the construction cost of the current address combination of the biomass power plants changes less than a preset change threshold, outputting the address combination of the biomass power plants generated this time;

[0011] The distance cost from all biomass locations to the nearest biomass storage station and the construction cost of the biomass storage stations under the address combination of the biomass storage stations are calculated according to the following formula:

[0012] ;

[0013] In the formula, is the sum of the distance cost and the construction cost in the biomass storage station stage, is the distance from a biomass location to the corresponding biomass storage station, is the biomass utilization rate, is the biomass carrying capacity of a unit vehicle, is the construction cost of a single biomass storage station, is the biomass density, n is the total number of biomass locations, m is the preset number of biomass storage stations, is the distance cost from a biomass location to the corresponding biomass storage station;

[0014] The distance cost from all biomass storage stations to the corresponding biomass power plant and the construction cost of the biomass power plants under the address combination of the biomass power plants are calculated according to the following formula:

[0015] ;

[0016] In the formula, is the sum of the distance cost and the construction cost in the biomass power plant stage, is the distance from a biomass storage station to the corresponding biomass power plant, is the biomass density, To improve biomass utilization, The distance cost from the biomass storage station to the corresponding biomass power plant. The construction cost of a single biomass power plant. The biomass carrying capacity per unit vehicle. For a pre-set number of biomass collection and storage stations, The number of biomass power plants is predetermined.

[0017] Preferably, the step of clustering and dimensionality reduction of the biomass distribution matrix of the preset region using weights specifically includes:

[0018] The weighted K-Means clustering algorithm is used to cluster and reduce the dimensionality of the biomass distribution matrix of the preset region. The objective function formula of the weighted K-Means clustering algorithm is:

[0019] ;

[0020] In the formula, For the number of clusters, For the first The set of points in a cluster; Indicates the first The weight of each data point; For the first One data point; For the first The center point of each cluster; Indicates the first From the data point to the The distance between cluster centers.

[0021] Preferably, the formulas for calculating the distance from all biomass locations to the nearest biomass collection and storage station, and the formulas for calculating the distance from all biomass collection and storage stations to the corresponding biomass power plants are as follows:

[0022] ;

[0023] In the formula, The average radius of the Earth, and For the first The latitude and longitude of each station, and For the first The latitude and longitude of each station.

[0024] Preferably, the biomass density is the sum of the biomass density of abandoned farmland, the biomass density of agricultural land, and the biomass density of forest land.

[0025] Preferably, the screening of the biomass collection and storage station address combinations specifically includes:

[0026] The L-BFGS-B optimization algorithm is used to iteratively generate address combinations of biomass storage stations with a preset number, minimize the sum of the distance cost and construction cost of the biomass storage stations, and search for the optimal address combination of the biomass storage stations under a preset number of iterations.

[0027] Preferably, the screening of the address combination of the biomass power plant specifically comprises:

[0028] The Nelder-Mead optimization algorithm is used to iteratively generate address combinations of biomass power plants with a preset number, minimize the sum of the distance cost and construction cost of the biomass power plants, and output the address combination of the biomass power plant generated this time when the change of the sum of the distance cost and construction cost of the address combination of the biomass power plant this time relative to the sum of the distance cost and construction cost of the address combination of the biomass power plant generated last time is less than a preset threshold.

[0029] Preferably, the generating of the set of candidate sites of the biomass power plant with a preset number along the line of the trunk road information specifically comprises:

[0030] An initial power plant set is generated along the line of the trunk road information, a weighted K-Means clustering algorithm is used to cluster and reduce the dimension of the initial power plant set, and a set of candidate sites of the biomass power plant with a preset number is generated.

[0031] The biomass storage and transportation site selection optimization method provided by the present application has at least the following beneficial effects:

[0032] In the biomass energy facility site selection, the present application first constructs a full-link cost accounting system, the cost calculation covers the full distance cost from the biomass site to the storage station, to the power plant, and also includes the construction cost of the storage station and the power plant, and innovatively introduces key parameters such as biomass utilization rate and unit vehicle carrying capacity to accurately quantify the cost, completely making up for the short board of traditional methods which only focus on a single link and miss core influencing factors. This complete and accurate cost accounting mechanism can provide solid economic data support for the site selection scheme, help decision-makers select the optimal scheme that is both economical and feasible, and effectively promote the realization of cost controllability and efficient landing of large-scale utilization of biomass energy.

[0033] Through the collaborative application of the LBFGSB algorithm and the Nelder-Mead algorithm, the limitation of traditional single algorithm easily falling into local optimal solution is effectively broken through, relying on the good adaptability of the two algorithms to multi-constrained and non-convex optimization problems, the global search of the site selection scheme is realized, and a better spatial layout of the storage station and the power plant is finally obtained. BRIEF DESCRIPTION OF DRAWINGS

[0034] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0035] Figure 1 is a flow chart of a biomass collection, storage and transportation site optimization method according to an embodiment of the present application;

[0036] Figure 2 is a schematic diagram of 1000 clustered biomass collection and storage site candidate locations according to an embodiment of the present application;

[0037] Figure 3 is a visualized schematic diagram of a biomass collection and storage site allocation matrix according to an embodiment of the present application;

[0038] Figure 4 is a certain place road data general map according to an embodiment of the present application;

[0039] Figure 5 is a schematic diagram of a certain place city main road screening result according to an embodiment of the present application;

[0040] Figure 6 is a certain place city main road map according to an embodiment of the present application;

[0041] Figure 7 is a schematic diagram of a certain place city main road map according to an embodiment of the present application;

[0042] Figure 8 is a schematic diagram of a certain place city main road map according to an embodiment of the present application;

[0043] Figure 9 is a schematic diagram of a certain place city main road map according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in conjunction with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0045] One embodiment of the present application relates to a biomass collection, storage and transportation site selection optimization method. The implementation details of the biomass collection, storage and transportation site selection optimization method of the present embodiment are described below. The following details are provided for easy understanding and are not essential for implementing the present embodiment.

[0046] The specific process of the biomass collection, storage and transportation site selection optimization method of the present embodiment can be as shown in Figure 1 , which includes:

[0047] Step 101: Obtain all biomass site data in the preset area and main road information; construct a biomass distribution matrix of the preset area by the geographic coordinates and biomass density in all biomass site data.

[0048] Define the research object as a set of N biomass sites, each site has a clear geographic coordinate attribute representing its spatial position. On this basis, a composite biomass density evaluation model is established to quantitatively analyze the resource endowment through three key indicators: represents the biomass density of abandoned farmland at site i , represents the biomass density of agricultural land at site i , represents the biomass density of forest land at site i . Finally, the comprehensive biomass density index of site i is constructed as the total biomass density , i.e. , forming a multi-dimensional resource evaluation matrix.

[0049] Site coordinates and biomass density distribution: First, extract the latitude and longitude information and the biomass density of abandoned farmland, agricultural land and forest land 、 、 of each site from the biomass distribution geographic data of a certain site after grid processing , and construct the input matrix X:

[0050] ;

[0051] Step 102: Set the weight of the corresponding biomass site based on the biomass density, and perform dimensionality reduction clustering on the preset area biomass distribution matrix through the weight, output a set of candidate sites containing a preset number of biomass collection and storage stations;

[0052] The weighted K-Means clustering algorithm is used to cluster and reduce the dimensionality of the biomass distribution matrix of the preset region. The objective function formula of the weighted K-Means clustering algorithm is:

[0053] ;

[0054] In the formula, For the number of clusters, For the first The set of points in a cluster; Indicates the first The weight of each data point; For the first One data point; For the first The center point of each cluster; Indicates the first From the data point to the The distance between cluster centers.

[0055] Candidate sites for biomass storage stations: Biomass location data consists of over 450,000 gridded biomass distribution locations. However, due to the large amount of biomass location data, which is difficult to fit, a weighted K-Means clustering method was used to cluster the data. A number of candidate locations were obtained, as follows: Figure 2 1000 candidate sites for biomass collection and storage stations after clustering In the diagram, different colored blocks represent different clusters, and the red cross in the middle of the colored block represents the center of each cluster. n 10 candidate locations.

[0056] The figure shows that, based on the clustering results of the biomass location data, biomass locations are sparser in the western part of a certain area and denser in the eastern part. Furthermore, the clustering results are very uniform, consistent with the algorithm's expected performance, effectively converting 450,000 biomass locations into almost 1,000 locations, thus reducing computational load.

[0057] Step 103: Based on the candidate location set of biomass collection and storage stations, iteratively generate address combinations containing a preset number of biomass collection and storage stations; filter the address combinations of biomass collection and storage stations, and use the minimum distance cost from all biomass locations to the nearest biomass collection and storage station and the minimum construction cost of the biomass collection and storage station under the address combination as the filtering objective to iteratively obtain the optimized biomass collection and storage station address combinations;

[0058] The formulas for the distance cost from all biomass sites to the nearest biomass storage station and the construction cost of the biomass storage station under the given combination of biomass storage station locations are as follows:

[0059] ;

[0060] In the formula, This is the sum of the stage distance cost and construction cost of the biomass collection and storage station. This represents the distance from the biomass location to the corresponding biomass collection and storage station. To improve biomass utilization, The biomass carrying capacity per unit vehicle. The construction cost of a single biomass collection and storage station, For biomass density, n The total number of biomass sites, m For a pre-set number of biomass collection and storage stations, The distance cost from the biomass location to the corresponding biomass collection and storage station;

[0061] The L-BFGS-B optimization algorithm is used to iteratively generate address combinations containing a preset number of biomass collection and storage stations, minimizing the sum of the distance cost and construction cost of the biomass collection and storage stations. Under a preset number of iterations, the optimal combination of collection and storage station addresses is found.

[0062] The formula for calculating the distance from all biomass locations to the corresponding biomass collection and storage stations is as follows:

[0063] ;

[0064] In the formula, It is the average radius of the Earth (6371 km). and For the first The latitude and longitude of each station, and It is the first The latitude and longitude of each station.

[0065] Assign locations to the nearest station: For each location, calculate the distance to all stations, assign it to the nearest station, and generate an assignment matrix. A ,in:

[0066] ;

[0067] A visual representation of the allocation matrix of biomass collection and storage stations is as follows: Figure 3 As shown in the figure, the dots represent clusters formed during data preparation. n =1000 candidate locations, with different colors reflecting different sizes; the larger the size, the greater the total amount of biomass. It is very clear that the phenomenon of decreasing biomass distribution from east to west in a certain area has not significantly affected the distribution of collection and storage sites. Therefore, the optimization of collection and storage sites is more dependent on transportation distance than on biomass quality, which is consistent with the algorithm's expectations and the actual situation.

[0068] Output the total cost of each biomass collection and storage station combination. and record the optimal result is 128.66 million yuan.

[0069] Step 104: generate a set of biomass power plant candidate sites containing a preset number of biomass power plants along the trunk road information, iteratively generate address combinations containing a preset number of biomass power plants; for each biomass power plant address combination, assign each biomass collection and storage station to the nearest biomass power plant, calculate the distance cost of all biomass collection and storage stations to the corresponding biomass power plant and the construction cost of the biomass power plant under the biomass power plant address combination; when the sum of the distance cost and the construction cost of the current biomass power plant address combination changes less than the preset change threshold, output the generated biomass power plant address combination this time;

[0070] Get the road data of a certain place and import it into the ArcGIS tool to get the total road data map of a certain place as shown in Figure 4 , which shows that the road density in the east of a certain place is much higher than that in the west. The screening result of the city trunk road of a certain place is shown in Figure 5 , which shows the city trunk road of a certain place; the city trunk road map of a certain place is shown in Figure 6 , which shows that the trunk road of a certain place is still much more in the east than in the west, and the trunk road in the west is sparse; the Figure 6 "Along the line to generate points" function is used and all points on the trunk road are taken to Excel. The schematic diagram of taking points along the city trunk road is shown in Figure 7 , which shows that the distribution of the taken points is relatively uniform in the road, but due to the intersection of the road, the number of taken points is obviously more than that in the road, which conforms to the actual situation, and the power plant should be built as much as possible in a place with convenient transportation (i.e. the possibility of selecting the intersection of the road in the optimization algorithm process is higher). However, due to the excessive repetition of the selected points at the intersection, a certain optimization is needed.

[0071] Due to the about 110,000 road-related candidate sites and the uneven distribution of the east and west of the trunk road, the distribution of the candidate sites presents the phenomenon of excessive repetition of the selected points and excessive aggregation in the east, which affects the optimization result, so the Kmeans clustering is used to cluster the candidate points into 1000 candidate sites, and the biomass power plant candidate site set is shown in Figure 8 , which shows that the clustering result of the candidate power plant shows that most of the clustering results are still in the trunk road, but the phenomenon of repetition of the selected points is very good. While still relying on the road, this phenomenon is effectively alleviated, which lays a good foundation for the subsequent optimization process.

[0072] The formula for calculating the distance cost of all biomass collection and storage stations to the corresponding biomass power plant and the construction cost of the biomass power plant under the biomass power plant address combination is as follows:

[0073] ;

[0074] In the formula, is the sum of the distance cost and the construction cost of the biomass power plant stage, is the distance from the biomass storage station to the corresponding biomass power plant, is the biomass density, is the biomass utilization rate, is the distance cost from the biomass storage station to the corresponding biomass power plant, is the construction cost of a single biomass power plant, is the biomass carrying capacity of a unit vehicle, is the preset number of biomass storage stations, is the preset number of biomass power plants.

[0075] The Nelder-Mead optimization algorithm is used to iteratively generate an address combination containing a preset number of biomass power plants, to minimize the sum of the distance cost and the construction cost of the biomass power plant, and when the sum of the distance cost and the construction cost of the current biomass power plant address combination is less than the preset threshold relative to the sum of the distance cost and the construction cost of the last generated biomass power plant address combination, the current generated biomass power plant address combination is output.

[0076] In the model established by the present application, is the number of storage stations; represents the total number of candidate power plants; the longitude and latitude coordinates of the th storage station are represented as ; is the biomass density (unit: ton / square kilometer) of the th storage station. A total of power plants need to be selected, wherein the longitude and latitude coordinates of the th power plant are . is the distance (unit: kilometers) from the th storage station to the th power plant, which can be calculated by the spherical distance formula. In the cost optimization model established, represents the construction cost of a single power plant (unit: yuan); represents the transportation cost per unit distance (unit: yuan / km); is the biomass carrying capacity of a unit transportation vehicle (unit: ton / vehicle). is the total cost, and the optimization objective of the present work is to find the minimum value of .

[0077] The distance formula from all biomass storage stations to the corresponding biomass power plants is as follows:

[0078] ;

[0079] In the formula, is the average radius of the earth (6371km), and is the latitude and longitude of the first station, and is the latitude and longitude of the first station. For each biomass collection and storage station, the distance to all biomass power plant addresses is calculated, assigned to the nearest power plant, and a distribution matrix is generated wherein:

[0080] A ;

[0081] The biomass power plant address optimization result is shown in , wherein the round dots in the figure represent

[0082] =200 optimized collection and storage stations, and different colors reflect different sizes, and the larger the size, the greater the total biomass represented. The macroscopic power plant site optimization result shows that there are more power plants in the east than in the west, and the reason is that the total biomass in the east is much larger than that in the west. From a micro perspective, each power plant ensures that the transportation cost of the collection and storage stations it is responsible for to it is minimized. The optimization result is very good. Figure 9 n The total cost of each biomass power plant address combination is output , and the optimal result is recorded

[0083] is 404820000 yuan. The step division of the above methods is only for clear description, and can be combined into one step or split into multiple steps in implementation, as long as the same logical relationship is included, and all are within the protection scope of the present application; adding insignificant modifications or introducing insignificant designs in the algorithm or process, but not changing the core design of the algorithm and process are within the protection scope of the present application.

[0084] Another embodiment of the present application relates to a computer readable storage medium storing a computer program. The computer program is executed by a processor to implement the above method embodiment.

[0085] Another embodiment of the present application relates to a computer readable storage medium storing a computer program. The computer program is executed by a processor to implement the above method embodiment.

[0086] ​That is, a person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment methods can be completed by a program instructing relevant hardware, the program being stored in a storage medium and including a plurality of instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0087] A person of ordinary skill in the art can understand that the above-mentioned embodiments are specific embodiments for implementing the present application, and in actual applications, various changes can be made in form and details without departing from the spirit and scope of the present application.

Claims

1. A method for optimizing the site selection of biomass collection, storage and transportation, characterized in that, The method comprises: acquiring all biomass site data in a preset area and trunk road information; constructing a biomass distribution matrix of the preset area based on geographic coordinates and biomass density in all biomass site data; setting a weight corresponding to a biomass site based on biomass density, clustering and reducing dimension of the biomass distribution matrix of the preset area by the weight, and outputting a candidate site set containing a preset number of biomass collection and storage stations; iteratively generating an address combination containing a preset number of biomass collection and storage stations based on the candidate site set of the biomass collection and storage stations; and screening the address combination of the biomass collection and storage stations to obtain an optimized address combination of the biomass collection and storage stations iteratively with a distance cost from all biomass sites to the nearest biomass collection and storage station and a construction cost of the biomass collection and storage stations under the address combination of the biomass collection and storage stations as a screening target; iteratively generating an address combination containing a preset number of biomass power plants based on a candidate site set containing a preset number of biomass power plants generated along a line through the trunk road information; and for each address combination of the biomass power plants, distributing each biomass collection and storage station to the nearest biomass power plant, calculating a distance cost from all biomass collection and storage stations to the corresponding biomass power plant and a construction cost of the biomass power plant under the address combination of the biomass power plant; and when a sum of the distance cost and the construction cost of the current address combination of the biomass power plant changes less than a preset change threshold, outputting the address combination of the biomass power plant generated this time; a formula of the distance cost from all biomass sites to the nearest biomass collection and storage station and the construction cost of the biomass collection and storage stations under the address combination of the biomass collection and storage stations is as follows: ； wherein, is the sum of the distance cost and the construction cost of the biomass collection and storage station phase, is the distance from the biomass site to the corresponding biomass collection and storage station, is the biomass utilization rate, is the biomass carrying capacity of a unit vehicle, is the construction cost of a single biomass collection and storage station, is the biomass density, n is the total number of biomass sites, m is the preset number of biomass collection and storage stations, is the distance cost from the biomass site to the corresponding biomass collection and storage station; a formula of the distance cost from all biomass collection and storage stations to the corresponding biomass power plant and the construction cost of the biomass power plant under the address combination of the biomass power plant is as follows: ； wherein, is the sum of the stage distance cost and the construction cost of the biomass power plant, is the distance from the biomass collection and storage station to the corresponding biomass power plant, is the biomass density, is the biomass utilization rate, is the distance cost from the biomass collection and storage station to the corresponding biomass power plant, is the construction cost of a single biomass power plant, is the biomass carrying capacity of a unit vehicle, is the preset number of biomass collection and storage stations, is the preset number of biomass power plants.

2. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, the clustering and reducing dimension of the biomass distribution matrix of the preset area by the weight specifically comprises: the clustering and reducing dimension of the biomass distribution matrix of the preset area by the weight specifically comprises: ； wherein is the number of clusters, is the set of points in the th cluster; denotes the weight of the th data point; is the th data point; is the center point of the th cluster; denotes the distance of the th data point to the center of the th cluster.

3. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, a target function formula in the weighted K-Means clustering algorithm is as follows: ； wherein is the average radius of the earth, and is the latitude and longitude of the th site, and is the latitude and longitude of the th site.

4. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, a formula of the distance from all biomass sites to the nearest biomass collection and storage station and a formula of the distance from all biomass collection and storage stations to the corresponding biomass power plant are as follows:

5. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, the biomass density is a sum of abandoned farmland biomass density, agricultural land biomass density and forest land biomass density. the screening of the address combination of the biomass collection and storage stations specifically comprises:

6. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, an L-BFGS-B optimization algorithm is used to iteratively generate an address combination containing a preset number of biomass collection and storage stations, minimize a sum of a distance cost and a construction cost of the biomass collection and storage stations, and search for an optimal address combination of the collection and storage stations under a preset number of iterations. the screening of the address combination of the biomass power plant specifically comprises: The Nelder-Mead optimization algorithm is used to iteratively generate an address combination of a preset number of biomass power plants, minimize the sum of the distance cost and the construction cost of the biomass power plants, and output the generated address combination of the biomass power plants when the sum of the distance cost and the construction cost of the address combination of the biomass power plants changes by less than a preset threshold relative to the sum of the distance cost and the construction cost of the address combination of the biomass power plants generated last time.

7. The biomass collection, storage, and transportation site optimization method of claim 1, wherein, The address combination of the preset number of biomass power plants is generated along the trunk road information, and specifically includes: An initial power plant set is generated along the trunk road information, and a weighted K-Means clustering algorithm is used to cluster and reduce the dimension of the initial power plant set to generate a set of candidate sites of biomass power plants containing a preset number of biomass power plants.

Images