A method for modeling garbage land deployment based on urban population mobility

Through the modeling of garbage land deployment based on urban population mobility, the use of gray prediction and multiple regression models to predict garbage production and evaluate garbage station capacity, the problem of garbage station scale and site selection is solved, and the effective utilization of garbage station resources and environmental impact is achieved. reduce.

CN113869606BActive Publication Date: 2024-11-08NANJING UNIV OF POSTS & TELECOMM +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111257398.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-27
Publication Date
2024-11-08
Estimated Expiration
2041-10-27

AI Technical Summary

Technical Problem

The scale and site selection of urban garbage stations lead to conflicts, affecting environmental and social stability. It is difficult for existing technology to effectively solve the negative impact of garbage stations on residents' living environment and unbalanced resource utilization.

Method used

Using the modeling method of garbage land deployment based on urban population mobility, we can collect and pre-treat population and garbage production data, establish a gray prediction model and a multivariate linear regression model, predict garbage production and evaluate the capacity threshold of garbage stations, and achieve effective garbage station resources. Utilization and capacity load balancing.

Benefits of technology

It improves the scientificity and rationality of garbage station site selection, reduces the occurrence of contradictions and conflicts, meets residents' living needs and reduces environmental impacts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113869606B_ABST
    Figure CN113869606B_ABST
Patent Text Reader

Abstract

A method for modeling the deployment of garbage land based on urban population flow, first collects and preprocesses the population and garbage production data of the community point to obtain the original data set; then establishes a gray prediction model and introduces a multiple linear regression model to predict the garbage production; finally, based on the predicted results of garbage production and the garbage production of previous years in the original data set, the capacity threshold of the garbage station that governs the community point is evaluated, so that the garbage station can be effectively utilized and the capacity load is balanced. This method combines the gray prediction model with the multiple regression model to improve the prediction effect, and at the same time combines the prediction results and historical data to obtain the capacity threshold evaluation, so as to achieve the effective utilization of urban garbage station construction resources and capacity load balance, so that the garbage station site selection problem is better solved, and the living needs of the surrounding community residents are met as much as possible while ensuring that there will be no environmental impact caused by garbage disposal.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer and application technology, and in particular to a method for modeling garbage land deployment based on urban population flow. Background Art

[0002] In recent years, with the development of cities and the increase in population, the amount of garbage produced in cities has also been increasing. In order to deal with these garbage in a timely manner and reduce environmental pollution, various places are vigorously promoting the construction of garbage disposal, sewage treatment and other facilities. On the one hand, with the increase of garbage disposal facilities, the city's garbage disposal capacity has been continuously improved, which has brought many conveniences to residents' lives; on the other hand, in the process of building or expanding garbage stations, a worrying phenomenon has also emerged: conflicts caused by the size of garbage stations have occurred one after another. The emergence of these conflicts or contradictions has not only affected the construction speed of garbage stations, but also hidden many social instability factors. Especially in recent years, environmental and social problems caused by the scale of garbage stations have gradually increased.

[0003] The scale and location of garbage stations belong to the location selection of NIMBY facilities. While NIMBY facilities bring benefits to the general public, they also bring negative impacts to nearby residents, and even become unwelcome to residents. For example, while garbage stations provide convenience to residents, the odor they emit also seriously affects the living environment of nearby residents. Therefore, garbage stations are often resisted by residents in the area, and even NIMBY conflicts arise. With the further development of urbanization and the gradual improvement of residents' rights awareness, the probability of NIMBY conflicts will certainly increase greatly. For NIMBY conflicts, avoidance and concealment are not good solutions. On the contrary, reasonable location selection of garbage stations can effectively reduce the impact of garbage stations on the environment of nearby residents and reduce the occurrence of contradictions or conflicts. Therefore, the location selection of garbage stations is extremely important. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a method for garbage land deployment modeling based on urban population flow.

[0005] A method for modeling garbage land deployment based on urban population flow includes the following steps:

[0006] Step 1: Collect and preprocess the population and garbage production data of the community points, extract features from the data, and obtain the original data set through correlation analysis, level verification and data correction;

[0007] Step 2: Based on the original data set obtained, a grey prediction model is established and a multivariate linear regression model is introduced to predict the garbage output;

[0008] Step 3: Based on the predicted results of garbage production obtained in step 2 and the garbage production in previous years in the original data set, the capacity threshold of the garbage station that governs the community point is evaluated, so that the garbage station can be effectively utilized and the capacity load is balanced.

[0009] Furthermore, the specific steps of step 1 are as follows:

[0010] Step 1-1, collect relevant data of the community point over the years, including the community's permanent population, total number of households, average number of people per household, in-migration population, out-migration population and garbage production;

[0011] Step 1-2: Generate a community point vector X for each year’s community point data based on the data collected in step 1-1 i , where 1≤i≤n, n is the number of community points, and the vector includes the permanent population x1, the total number of households x2, the average number of people per household x3, the in-migrant population x4, the out-migrant population x5 and the garbage output x6;

[0012] Step 1-3, for the obtained community point vector X i For correlation analysis, the value range of the correlation coefficient γ is -1≤γ≤1. When γ≥0, it is a positive correlation, otherwise it is a negative correlation.

[0013] Correlation analysis uses the Pearson correlation coefficient, which is used to analyze the relationship between two continuous variables. It is a linear correlation coefficient and the calculation formula is:

[0014]

[0015] Among them, x i and i is the standard score of the sample, and is the sample mean, n is the number of samples.

[0016] Steps 1-4, for the community point vector X i Perform level check and obtain the level ratio ρ(k) (all ρ(k) must fall within the interval The community point vector X that meets the conditions i Add to the original data set X; for the community point vector X that does not meet the conditions i Perform data correction, and then repeat steps 1-4 for recalibration, where 1≤i≤n;

[0017] The formula for calculating the level ratio of a data series is:

[0018]

[0019] Among them, ρ(k) is the level ratio, x (0) (k) and x(0) (k+1) is the neighbor mean.

[0020] Step 1-5, the data preprocessing of step 1-4 is used to obtain the original data set X = {X1, X2, ..., X M}, where M is the number of community points.

[0021] Furthermore, in step 2, the GM (1, 1) model is applied in the grey prediction model.

[0022] Furthermore, the specific steps of step 2 are as follows:

[0023] Step 2-1: for each item X in the original data set X i Each field x j Doing the first-order addition, we get:

[0024] where 1≤j≤6

[0025] Again Perform mean processing to obtain the mean generated column:

[0026]

[0027] in,

[0028] 2≤i≤n,1≤j≤6

[0029] Step 2-2, construct data matrix B j and data vector Y j :

[0030]

[0031] And use the least squares method to solve the coefficients and in is called the development coefficient, It is called the gray action, and the solution formula is:

[0032]

[0033] Finally, the grey prediction model is obtained:

[0034]

[0035] Step 2-3: For the grey prediction model obtained in step 2-2, a multivariate linear regression model is introduced to predict the future garbage production of the community point. The expression is:

[0036]

[0037] in, is the result set, which is the result that the function module needs to calculate, that is, the predicted result of the future garbage production of the community point. Composed feature set, is the regression coefficient, is a random error and follows a normal distribution N(0,σ 2 ).

[0038] Step 2-4: According to the final result, the garbage production of all community points in the area is predicted by using the gray prediction plus multivariate regression model to obtain the predicted garbage production value T of the community point. i , where there are M community points in the area, 1≤i≤M.

[0039] Furthermore, the specific steps of step 3 are as follows:

[0040] Step 3-1: Collect the predicted value of garbage production T of the community point obtained in step 2 i , and the garbage production data H for this year already in the original data set i ;

[0041] Step 3-2, using the formula Get the capacity threshold C of the garbage station that governs the area, where T i is the predicted value of garbage production at the community point, α i The impact factor of the community point on the garbage station capacity threshold assessment;

[0042] Step 3-3, complete the regional garbage site capacity threshold assessment and end the process.

[0043] The beneficial effects achieved by the present invention are as follows: by combining the grey prediction model with the multivariate regression model, the prediction effect is improved, and at the same time, the prediction results and historical data are combined to obtain the capacity threshold evaluation, thereby achieving the effective utilization of urban garbage station construction resources and capacity load balancing, so that the garbage station site selection problem is better solved, and the living needs of the residents in the surrounding communities are met as much as possible while ensuring that there is no environmental impact caused by garbage disposal. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The flowchart is a step chart of collecting and preprocessing relevant data of community points in an embodiment of the present invention.

[0045] Figure 2 The figure is a flowchart of the steps of grey prediction plus multivariate regression for predicting garbage output in an embodiment of the present invention.

[0046] Figure 3 A flow chart of the steps for quantifying garbage sites in garbage land deployment in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0048] The present invention discloses a method for modeling garbage land deployment based on urban population flow, which specifically includes the following three parts.

[0049] 1. Collect and preprocess the relevant data of community points, and extract features from the relevant data of community points.

[0050] The specific steps are as follows:

[0051] Step 1: Collect relevant data of the community point over the years, including the community’s permanent population, total number of households, average number of people per household, in-migration population, out-migration population, garbage production and other data characteristics.

[0052] Step 2: Generate a community point vector X for each year’s community point data based on the data features collected in step 1 i , where 1≤i≤n, the vector includes the fields of permanent population x1, total number of households x2, average number of people per household x3, in-migrant population x4, out-migrant population x5 and garbage production x6.

[0053] Step 3: For the obtained community point vector X i For correlation analysis, the value range of the correlation coefficient γ is -1≤γ≤1. When γ≥0, it is a positive correlation, otherwise it is a negative correlation.

[0054] Correlation analysis uses the Pearson correlation coefficient, which is used to analyze the relationship between two continuous variables. It is a linear correlation coefficient and the calculation formula is:

[0055]

[0056] Among them, x i and i is the standard score of the sample, and is the sample mean, n is the number of samples.

[0057] Step 4: For the community point vector X i Perform level verification and obtain the level ratio ρ(k) (all ρ(k) fall within the interval ), the community point vector X that meets the conditions i Add to the original data set X; for the community point vector X that does not meet the conditions i Make data corrections.

[0058] The formula for calculating the level ratio of a data series is:

[0059]

[0060] Among them, ρ(k) is the level ratio, x (0) (k) and x (0) (k+1) is the neighbor mean.

[0061] Step 5: Preprocess the data in step 4 to obtain the original data set X = {X1, X2, ..., X M}, where M is the number of community points.

[0062] Second, the gray prediction plus multiple regression model for predicting garbage production, by identifying the differences in the development trends of various factors in the system, using the original values ​​with system representative characteristics for processing, to find the internal change rules of the system, and by establishing differential equations to solve, predict the future trend of garbage production. In the gray prediction model, the GM (1, 1) model is widely used.

[0063] The specific steps are as follows:

[0064] Step 1: For each item X of the original data set X obtained from the previous functional module i Each field x j Doing the first-order addition, we get:

[0065] where 1≤j≤6

[0066] Again Perform mean processing to obtain the mean generated column:

[0067]

[0068] in,

[0069] Step 2: Construct the data matrix and data vector

[0070]

[0071] And use the least squares method to solve the coefficients and in is called the development coefficient, It is called the gray action, and the solution formula is:

[0072]

[0073] Finally, the prediction model is obtained:

[0074]

[0075] That is, the future data feature values ​​of community points can be predicted.

[0076] Step 3: In order to make the prediction results more accurate, this function module introduces a multivariate linear regression model to predict the future garbage production of the community point. The expression is:

[0077]

[0078] in, is the result set, which is the result that the function module needs to calculate, that is, the predicted result of the future garbage production of the community point. Composed feature set, is the regression coefficient, is a random error and follows a normal distribution N(0,σ 2 ).

[0079] Step 4: According to the final gray prediction plus multivariate regression model, the garbage production of all community points in the area is predicted to obtain the predicted value of garbage production T of the community point. i , where there are M community points in the area, 1≤i≤M.

[0080] 3. The quantitative part of garbage stations in garbage land deployment mainly combines the predicted results of garbage production of a community point in the next year obtained from the previous functional module and the garbage production of the community point in previous years to conduct capacity threshold assessment on the garbage stations that govern the community point, so as to achieve effective utilization of urban garbage station construction resources and capacity load balancing.

[0081] Step 1: Collect the predicted garbage production value T of the community point obtained in step 2 i , and the garbage production data H for this year already in the original data set i ;

[0082] Step 2: Use the formula Get the capacity threshold C of the garbage station that governs the area, where T i is the predicted value of garbage production at the community point, α i The impact factor of the community point on the garbage station capacity threshold assessment;

[0083] Step 3: Complete the regional garbage site capacity threshold assessment and end the process.

[0084] The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiment. Any equivalent modifications or changes made by ordinary technicians in this field based on the contents disclosed by the present invention should be included in the protection scope recorded in the claims.

Claims

1. A method for modeling garbage land deployment based on urban population flow, characterized by: The method comprises the following steps: Step 1: Collect and preprocess the population and garbage production data of the community points, extract features from the data, and obtain the original data set through correlation analysis, level verification and data correction; The specific steps of step 1 are as follows: Step 1-1, collect relevant data of the community point over the years, including the community's permanent population, total number of households, average number of people per household, in-migration population, out-migration population and garbage production; Step 1-2: Generate community point vectors for each year’s community point data based on the data collected in step 1-1 in n is the number of years to be counted, and the vector includes the permanent population x1, the total number of households x2, the average number of people per household x3, the number of immigrants x4, the number of emigrants x5 and the amount of garbage produced x6; Steps 1-3: The obtained community point vector For correlation analysis, the value range of the correlation coefficient γ is -1≤γ≤1. When γ≥0, it is a positive correlation, otherwise it is a negative correlation. Correlation analysis uses the Pearson correlation coefficient, which is used to analyze the relationship between two continuous variables. It is a linear correlation coefficient and the calculation formula is: in, and is the standard score of the sample, and is the sample mean, n is the number of samples; Steps 1-4, community point vector Perform level verification to obtain the level ratio ρ(k), and all ρ(k) fall within the interval Community point vector that meets the conditions Add to the original data set X; for the community point vectors that do not meet the conditions Perform data correction, and then repeat steps 1-4 for recalibration, where 1≤i≤n; The formula for calculating the level ratio of a data series is: Among them, ρ(k) is the level ratio, x (0) (k) and x (0) (k+1) is the neighbor mean; Step 1-5, the data preprocessing of step 1-4 is used to obtain the original data set X = {X1, X2, ..., X M }, where M is the number of community points; Step 2: Based on the original data set obtained, a grey prediction model is established and a multivariate linear regression model is introduced to predict the garbage output; In step 2, the GM (1,1) model is applied in the grey prediction model; Step 3: Based on the predicted results of garbage production obtained in step 2 and the garbage production in previous years in the original data set, the capacity threshold of the garbage station that governs the community point is evaluated, so that the garbage station can be effectively utilized and the capacity load is balanced; The specific steps of step 3 are as follows: Step 3-1: Collect the predicted garbage production values ​​of the community points obtained in step 2 And the garbage production data for this year already in the original dataset Step 3-2, using the formula Get the garbage site capacity threshold C of the jurisdiction area, where is the predicted value of garbage production at the community point, The impact factor of the community point on the garbage station capacity threshold assessment; Step 3-3, complete the regional garbage site capacity threshold assessment and end the process.

2. The method for modeling garbage land deployment based on urban population flow according to claim 1 is characterized by: The specific steps of step 2 are as follows: Step 2-1, for each item in the original data set X Each field x j Doing the first-order addition, we get: in Again Perform mean processing to obtain the mean generated column: in, Step 2-2, construct the data matrix and data vector And use the least squares method to solve the coefficients and in is called the development coefficient, It is called the gray action, and the solution formula is: Finally, the grey prediction model is obtained: Step 2-3: For the grey prediction model obtained in step 2-2, a multivariate linear regression model is introduced to predict the future garbage production of the community point. The expression is: in, is the result set, which represents the predicted result of the future garbage production of the community point. Composed feature set, is the regression coefficient, is a random error and follows a normal distribution N(0,σ 2 ); Step 2-4: According to the final result, the garbage production of all community points in the area is predicted by using gray prediction plus multivariate regression model to obtain the predicted value of garbage production of the community points. There are M community points in the area.