A bottom-up carbon emission prediction method for domestic waste treatment solutions

Abstract

The present invention provides a bottom-up carbon emission prediction method for a domestic waste treatment scheme, which relates to the field of carbon emission technology. The method comprises: obtaining a first historical time series including the numerical values ​​of domestic waste generation in a target area at multiple historical moments and a second historical time series including the numerical values ​​of domestic waste influencing factors at multiple historical moments; obtaining the correlation between the first historical time series and the second historical time series, and determining the target influencing factors; determining a second prediction time series of the target influencing factors in a target prediction period based on the second historical time series corresponding to the target influencing factors, and determining the first prediction time series based on the second prediction time series; determining the unit greenhouse gas emissions at each preset moment based on the waste treatment parameters in the domestic waste treatment scheme; and determining the carbon emission prediction result of the domestic waste treatment scheme based on the second prediction time series and the unit greenhouse gas emissions. The present invention can improve the accuracy of the carbon emission prediction result.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission technology, and in particular to a bottom-up carbon emission prediction method for a domestic waste treatment solution. Background Art

[0002] The existing methods for calculating carbon emissions from domestic waste disposal, i.e. greenhouse gas emissions, are mainly based on carbon emission factors, which are mostly used for macro-calculation of regional carbon emissions. However, due to the availability of local data, most of them use emission factors at the national or regional level, making it difficult to obtain carbon emission factors with local characteristics. The carbon emission prediction results in the existing technology are decoupled from the local domestic waste characteristics, affecting the accuracy of the carbon emission prediction results. Summary of the invention

[0003] The present invention provides a bottom-up carbon emission prediction method for a domestic waste treatment solution, so as to solve the defect of inaccurate carbon emission prediction results in the prior art and improve the accuracy of carbon emission prediction results.

[0004] The present invention provides a bottom-up method for predicting carbon emissions from domestic waste treatment solutions, the method comprising:

[0005] Obtaining a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in a target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments;

[0006] Obtaining the correlation between the first historical time series and each of the second historical time series, and determining at least one target influencing factor among each of the domestic waste influencing factors based on the correlation;

[0007] Based on the second historical time series corresponding to the target influencing factor, determine the second prediction time series of the target influencing factor in the target prediction period, and based on each of the second prediction time series, determine the first prediction time series, the first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time in the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factor in the target area at each preset time;

[0008] Determining the unit greenhouse gas emissions at each preset time based on the waste treatment parameters in the domestic waste treatment plan of the target area, wherein the domestic waste treatment plan includes the waste treatment parameters at each preset time, and the waste treatment parameters reflect the proportion of domestic waste using various domestic waste treatment methods, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating a unit weight of domestic waste;

[0009] Based on the second prediction time series and the unit greenhouse gas emissions, the carbon emission prediction result of the domestic waste treatment solution is determined.

[0010] According to a bottom-up carbon emission prediction method for a domestic waste treatment solution provided by the present invention, the step of obtaining the correlation between the first historical time series and each of the second historical time series includes:

[0011] Grey correlation analysis is performed on the first historical time series and each of the second historical time series to obtain the correlation between the first historical time series and each of the second historical time series.

[0012] According to a bottom-up carbon emission prediction method for a domestic waste treatment solution provided by the present invention, the second historical time series corresponding to the target influencing factor is determined based on the second historical time series, and the second predicted time series of the target influencing factor in the target prediction period is determined, including:

[0013] implement The second target operation is performed to obtain the second predicted time series, and each of the second target operations includes the following steps:

[0014] Performing an m-order accumulation operation on the current second time series to obtain a second processed time series;

[0015] Predicting the next value of the last value in the second processing time series based on the second processing time series, and adding it to the second processing time series;

[0016] Performing an m-order cumulative subtraction operation on the second processing time series to obtain an updated second time series;

[0017] The second time series is a combination of the second historical time series and the second predicted time series. In the first second target operation, the second time series is the second historical time series. Is a positive integer.

[0018] According to a bottom-up carbon emission prediction method for a domestic waste treatment solution provided by the present invention, the first prediction time series is determined based on each of the second prediction time series, including:

[0019] implement The first target operation is performed to obtain the first predicted time series, and each time the first target operation is performed, the following steps are included:

[0020] Performing an m-order accumulation operation on the current first time series to obtain a first processed time series;

[0021] Predicting the next value of the last value in the first processing time series based on the first processing time series and the second processing time series, and adding the next value to the first processing time series;

[0022] Performing an m-order cumulative subtraction operation on the first processing time series to obtain an updated first time series;

[0023] The first time series is a combination of the first historical time series and the first predicted time series, and in the first first target operation, the first time series is the first historical time series.

[0024] According to a bottom-up method for predicting carbon emissions of a domestic waste treatment solution provided by the present invention, the second historical time series corresponding to the target influencing factor is determined to be before the second prediction time series of the target prediction period, including:

[0025] Based on multiple sample time series groups, the particle swarm algorithm is used to find the optimal solution and determine the value of m;

[0026] The sample time series group includes a sample first historical time series and a sample second historical time series.

[0027] According to a bottom-up carbon emission prediction method for domestic waste treatment solutions provided by the present invention,

[0028] The step of determining the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emission includes:

[0029] Integrating the fitting function based on the amount of domestic waste processed in the second prediction time series to obtain the carbon emission prediction result;

[0030] The fitting function is a function obtained by fitting the unit greenhouse gas emission corresponding to the waste treatment parameters at each preset time in the domestic waste treatment plan.

[0031] The present invention also provides a bottom-up carbon emission prediction device for domestic waste treatment solutions, the device comprising:

[0032] A historical data acquisition module, used to acquire a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in a target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments;

[0033] a target factor determination module, configured to obtain the correlation between the first historical time series and each of the second historical time series, and determine at least one target influencing factor from each of the domestic waste influencing factors based on the correlation;

[0034] A garbage quantity prediction module, configured to determine a second prediction time series of the target influencing factor in a target prediction period based on the second historical time series corresponding to the target influencing factor, and determine a first prediction time series based on each of the second prediction time series, wherein the first prediction time series reflects the predicted value of the amount of domestic garbage generated in the target area at each preset time in the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factor in the target area at each of the preset time;

[0035] a unit greenhouse gas emission prediction module, for determining the unit greenhouse gas emission at each preset time based on the waste treatment parameters in the domestic waste treatment scheme of the target area, wherein the domestic waste treatment scheme includes the waste treatment parameters at each preset time, and the waste treatment parameters reflect the proportion of domestic waste using various domestic waste treatment methods, and the unit greenhouse gas emission is the greenhouse gas emission generated by treating a unit weight of domestic waste;

[0036] A carbon emission prediction module is used to determine the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emissions.

[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the bottom-up carbon emission prediction method for domestic waste treatment solutions as described in any one of the above-mentioned methods is implemented.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the bottom-up carbon emission prediction methods for domestic waste treatment solutions as described above.

[0039] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the bottom-up methods for predicting carbon emissions from domestic waste treatment solutions as described above.

[0040] The bottom-up method for predicting carbon emissions from domestic waste treatment schemes provided by the present invention obtains the correlation between a first historical time series consisting of numerical values ​​of domestic waste generation in a target area at multiple historical moments and a second historical time series consisting of numerical values ​​of domestic waste influencing factors in the target area at multiple historical moments, and determines at least one target influencing factor among the domestic waste influencing factors based on the correlation, so that the target influencing factor that has a relatively large impact on the domestic waste generation in the target area can be determined according to the actual local conditions of the target area, and then the numerical values ​​of the target influencing factors at future moments are predicted based on the second historical time series of the target influencing factors to obtain a second predicted time series, and a first predicted time series reflecting the domestic waste generation in the target area at future moments is obtained based on the second predicted time series, and the unit greenhouse gas emissions at each moment are determined according to the waste treatment parameters at different moments within the target prediction period in the domestic waste treatment scheme, and the carbon emission prediction results of the domestic waste treatment scheme that adopts a combination of various domestic waste disposal methods to treat domestic waste are predicted based on the first predicted time series and the unit greenhouse gas emissions, which can effectively improve the accuracy of carbon emission prediction for domestic waste treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is one of the flow charts of the bottom-up carbon emission prediction method for domestic waste treatment scheme provided by the present invention.

[0043] Figure 2 This is the second flow chart of the bottom-up carbon emission prediction method for domestic waste treatment provided by the present invention.

[0044] Figure 3 It is a schematic diagram of the domestic waste logistics network in the bottom-up domestic waste treatment scheme carbon emission prediction method provided by the present invention.

[0045] Figure 4 It is a structural schematic diagram of a carbon emission prediction device for a bottom-up domestic waste treatment solution provided by the present invention.

[0046] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Combine the following Figure 1-3 The present invention describes the bottom-up carbon emission prediction method for domestic waste treatment solutions. Figure 1 As shown, the bottom-up carbon emission prediction method for domestic waste treatment scheme provided by the present invention comprises the following steps:

[0049] S110, obtaining a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in the target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments;

[0050] S120, obtaining the correlation between the first historical time series and each second historical time series, and determining at least one target influencing factor from each domestic waste influencing factor based on the correlation;

[0051] S130, based on the second historical time series corresponding to the target influencing factor, determine the second prediction time series of the target influencing factor in the target prediction period, and based on each second prediction time series, determine the first prediction time series, the first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time in the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factor in the target area at each preset time;

[0052] S140, determining unit greenhouse gas emissions at each preset time based on the garbage treatment parameters in the domestic garbage treatment plan of the target area, the domestic garbage treatment plan includes the garbage treatment parameters at each preset time, the garbage treatment parameters reflect the proportion of domestic garbage using various domestic garbage treatment methods, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating a unit weight of domestic garbage;

[0053] S150. Determine the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emissions.

[0054] like Figure 2As shown, the method provided by the present invention models the domestic waste treatment process from the bottom up based on the life cycle of domestic waste, and comprehensively predicts the potential carbon emissions generated by domestic waste treatment solutions from the two dimensions of "quantity" and "quality". Different domestic waste treatment solutions can be evaluated and optimized through the carbon emission prediction results to achieve low-carbon, efficient and sustainable management of urban domestic waste. In the "quantity" dimension, the amount of domestic waste generated is predicted, and in the "quality" dimension, the domestic waste treatment methods in different domestic waste treatment solutions are predicted. These two dimensions are explained in detail below.

[0055] In the method provided by the present invention, historical data of the target area are collected to obtain a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in the target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments, and the time interval between two adjacent historical moments is a preset value, such as one month, one year, etc. The number of historical moments included in the first historical time series and the second historical time series is consistent.

[0056] Domestic waste influencing factors are factors that affect the amount of domestic waste generated. There are many factors that affect the amount of domestic waste generated, such as per capita consumer expenditure of residents, number of permanent residents, per capita disposable income of residents, etc. Even if it is the same domestic waste influencing factor, its influence on the amount of domestic waste generated may be different in different regions. The method provided by the present invention determines the target influencing factor with a greater influence on the amount of domestic waste generated in the target region based on the actual historical data of the target region.

[0057] It is understandable that obtaining the correlation between the first historical time series and the second historical time series can be achieved by an existing quantitative correlation analysis method. In one implementation of the method provided by the present invention, obtaining the correlation between the first historical time series and the second historical time series based on a grey correlation analysis method specifically includes:

[0058] Grey correlation analysis is performed on the first historical time series and each second historical time series to obtain the correlation between the first historical time series and each second historical time series.

[0059] Grey correlation analysis provides a quantitative measure of the system development and change trend, which is very suitable for dynamic process analysis and can improve the accuracy of determining the target influencing factors in the method provided by the present invention. The grey correlation analysis between the first historical time series and the second historical time series can be expressed by the formula:

[0060] ;

[0061] in, express and The correlation between is the first historical time series, is the i-th second historical time series, represents the kth value in the first historical moment sequence, represents the kth value in the i-th second historical time series, n is the total number of historical moments in the first historical time series or the second historical time series, represents the resolution coefficient, =0.5.

[0062] Taking the statistical data of a southern city from 2013 to 2023 as an example, the calculation results of the correlation between different domestic waste influencing factors and the amount of domestic waste generated are shown in Table 1.

[0063] Table 1

[0064]

[0065] By comparing the correlations between each second historical time series and the first historical time series, at least one domestic waste influencing factor with a higher correlation can be selected as a representative influencing factor, that is, a target influencing factor.

[0066] The target prediction period is the period for which carbon emission prediction is required. After determining the target influencing factors, the values ​​of the target influencing factors at each preset moment in the target prediction period are predicted based on the second historical time series of the target influencing factors to obtain the second prediction time series. Then, based on the second prediction time series and the first historical time series, the amount of domestic waste generated at each preset moment in the target prediction period is predicted to obtain the first prediction time series. The time interval between adjacent preset moments is consistent with the time interval between adjacent historical moments, which can be one year, one month, etc.

[0067] Specifically, based on the second historical time series corresponding to the target influencing factor, determining the second predicted time series of the target influencing factor in the target prediction period includes:

[0068] implement The second target operation is performed to obtain a second predicted time series. In each second target operation, the following steps are included:

[0069] Performing an m-order accumulation operation on the current second time series to obtain a second processed time series;

[0070] Predicting the next value of the last value in the second processing time series based on the second processing time series, and adding it to the second processing time series;

[0071] Performing an m-order cumulative subtraction operation on the second processing time series to obtain an updated second time series;

[0072] The second time series is a combination of the second historical time series and the second predicted time series. In the first second target operation, the second time series is the second historical time series. Is a positive integer.

[0073] When the first second target operation starts, the second time series is the second historical time series. After each second target operation ends, a value is added to the second time series, that is, a value in the second prediction time series is added. Suppose the second time series is a time series including n moments, expressed as , perform m-order accumulation to generate the second processing time series. Based on the existing n values ​​in the second processing time series, the prediction of the n+1th value can be expressed as:

[0074] ;

[0075] Among them, a and b are parameters, which can be estimated by using the existing data in the second historical time series through least squares estimation. The minimum sum of squares of the errors between is the n+1th value in the second processing time series.

[0076] After obtaining the n+1th value in the second processing time series, perform an m-order cumulative subtraction operation on the second processing time series including n+1 values, so that a second time series including n+1 values ​​can be obtained. The second target operation can include the addition of The second time series of values, with respect to the second historical time series, is newly added The values ​​are the values ​​in the second forecast time series.

[0077] After obtaining the second prediction time series of each target influencing factor, further based on the second prediction time series of each target influencing factor and the first historical time series of the domestic waste generation, a second prediction time series of the domestic waste generation is generated, specifically including:

[0078] implement The first target operation is performed to obtain a first predicted time series. In each first target operation, the following steps are included:

[0079] Performing an m-order accumulation operation on the current first time series to obtain a first processed time series;

[0080] Predicting the next value of the last value in the first processing time series based on the first processing time series and the second processing time series, and adding it to the first processing time series;

[0081] Performing an m-order cumulative subtraction operation on the first processing time series to obtain an updated first time series;

[0082] The first time series is a combination of the first historical time series and the first predicted time series. In the first first target operation, the first time series is the first historical time series.

[0083] At the beginning of the first first target operation, the first time series is the first historical time series. Each time the first target operation is performed, a value is added to the first time series. From the previous description, it can be seen that the second processing time series is a sequence obtained by performing an m-order accumulation operation on the sequence obtained by combining the second historical time series and the second predicted time series. Each time the next value of the last value in the first processing time series is predicted based on the first processing time series and the second processing time series, the value in the second processing time series corresponding to the current moment of the first processing time series is used. Specifically, assuming that the first time series is , the second processing time series corresponding to the i-th target influencing factor is: , N is the total number of target influencing factors, then based on the existing n values ​​in the first processing time series, the prediction of the n+1th value can be expressed by the formula:

[0084] ;

[0085] in, represents the n+1th value in the first processing time series, , As a parameter, the formula can be obtained by using the existing data in the first historical time series and the second historical time series through least squares estimation. The sum of squares of the errors is minimized. is the value in the sequence of the nearest mean of the first processed time series, .

[0086] After obtaining the n+1th value in the first processing time series, perform an m-order cumulative subtraction operation on the first processing time series including n+1 values, so that the first time series including n+1 values ​​can be obtained. The first target operation can include the addition of The first time series of values, the newly added The values ​​are the values ​​in the first forecast time series.

[0087] It can be seen from the above description that when generating the first prediction time series and the second prediction time series, it is necessary to perform an m-order accumulation operation on the sequences. In order to select a better value of m and make the prediction result more accurate, the method provided by the present invention optimizes the value of m in advance, specifically including:

[0088] Based on multiple sample time series groups, the particle swarm algorithm is used to find the optimal solution and determine the value of m;

[0089] The sample time series group includes a sample first historical time series and a sample second historical time series.

[0090] When the particle swarm algorithm is used to optimize the value of m, a value of m can be regarded as a particle. The fitness function of the particle is based on the prediction accuracy of the value of m corresponding to the particle. The prediction accuracy can be tested by the mean absolute percentage error (MAPE). When MAPE < 10%, the accuracy is considered to be excellent.

[0091] After obtaining the second prediction time series, the carbon emissions of different domestic waste treatment schemes can be predicted based on the prediction results of the domestic waste generation amount. Specifically, each domestic waste treatment scheme includes waste treatment parameters at each preset time in the target prediction period, and the waste treatment parameters reflect the proportion of domestic waste amount of various domestic waste disposal methods.

[0092] In the method provided by the present invention, the domestic waste treatment plan includes waste treatment parameters at multiple times, thereby taking into account the time scale of the domestic waste treatment plan and the impact of the implementation time of the domestic waste treatment plan on carbon emissions, and the effectiveness of waste management strategy formulation at different stages can be evaluated.

[0093] Specifically, in the method provided by the present invention, the waste treatment parameters include the waste source classification rate, the proportion of food waste entering anaerobic digestion resource utilization treatment after classification, and the proportion of mixed waste entering incineration disposal. The method provided by the present invention uses the life cycle assessment (LCA) method to calculate the carbon emissions generated by treating 1 ton of domestic waste under different domestic waste disposal results, so as to evaluate the impact of the "quality" dimension of urban domestic waste disposal solutions. By introducing the variable , and Simulate the dynamically changing urban domestic waste logistics network and construct an LCA model including four disposal processes: source classification, anaerobic digestion, recycling, incineration and landfill. is the rate of waste source separation, Represents the proportion of classified food waste entering anaerobic digestion and resource utilization treatment, Represents the proportion of mixed waste entering incineration disposal. This method assumes that mixed waste in the domestic waste disposal system can enter two types of facilities: incineration or landfill. Therefore, the proportion of landfill disposal is In the method provided by the present invention, the domestic waste logistics network constructed is as follows: Figure 3 shown.

[0094] The method provided by the present invention selects a unit weight of domestic waste, such as 1 ton of domestic waste, as a functional unit (FU) to evaluate the impact of the disposal system. The LCA system boundary describes the entire process from the generation to the disposal of domestic waste. According to the source classification rate parameter Calculate the mass of the three types of waste obtained after classification: food waste, recyclable waste and other waste, and divide the logistics through recycling disposal, anaerobic digestion and incineration disposal facilities into disposal volume ( )、Remaining amount( ) and waste volume ( ), respectively representing the amount of garbage disposed of by the facility, the amount of garbage that cannot be disposed of due to capacity limitations and needs to be transferred to other facilities for disposal, and the amount of waste generated after disposal. The network also takes into account the distribution and changes in the quality and properties of domestic waste logistics. The model assumes that the properties of the input logistics remain unchanged, and uses mass balance or carbon balance to distribute logistics according to whether chemical conversion occurs in different disposal processes.

[0095] The prediction of unit greenhouse gas emissions corresponding to the domestic waste treatment scheme can be calculated based on the life cycle emission inventory of the domestic waste treatment system. The life cycle emission inventory of the domestic waste disposal system can be obtained according to the data release of different cities. In this method, S City is taken as an example, and the life cycle inventory data for the disposal of 1 ton of domestic waste is provided in combination with literature research and Ecoinvent 3.0 database. The greenhouse gas emission impact is calculated using the ReCiPe midpoint method. In the accounting, only the impact of fossil carbon emissions is considered. The impact of the recycling process of recyclable waste is excluded from the accounting system through mass allocation, and only the carbon emission impact of the other three disposal processes is considered. All waste residues generated in the system, including sludge, fly ash and bottom ash, will enter the landfill, while leachate and other waste liquids will be discharged to urban sewage treatment.

[0096] The amount of domestic waste entering the system is set to 1 ton. , and The three variables are used to analyze the life cycle assessment results under different domestic waste disposal structures. Due to the current limited manual sorting capacity, the domestic waste source classification rate parameter The value range of is set to 0% ~ 70%; and It can be set to any value between 0% and 100%. By increasing the values ​​of these two variables, we can reflect the future management strategy of urban domestic waste and evaluate the effectiveness of the "zero waste city" construction plan aimed at achieving resource recovery and reducing landfill load.

[0097] Specifically, the carbon emission prediction results of the domestic waste treatment scheme in the target area are determined based on the second prediction time series, including:

[0098] Integrating the fitting function based on the amount of domestic waste processed in the second prediction time series to obtain a carbon emission prediction result;

[0099] Among them, the fitting function is a function obtained by fitting the unit greenhouse gas emissions corresponding to the garbage treatment parameters at each preset moment in the domestic garbage treatment plan, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating a unit weight of domestic garbage.

[0100] In the method provided by the present invention, the amount of domestic waste generated and the life cycle carbon emissions based on the waste disposal structure are used as the influencing factors representing the "quantity" effect and "quality" effect in the urban domestic waste disposal system, respectively, and the two are independent of each other. and The value is set according to the local waste management policy. For example, the targets for the household waste classification rate and kitchen waste utilization rate in SZ City in 2025 are 50% and 45% respectively; The value can be set to 0 or 100% to discuss whether the city prefers landfill or incineration strategies. and The growth of is linear, and the phased targets of multiple time nodes within the time range can be obtained according to the implementation time of different plans. Therefore, the cumulative greenhouse gas emissions generated by a specific domestic waste disposal plan within a certain time range can be calculated by the definite integral of the unit waste disposal carbon emission change function based on the amount of waste generated. The calculation method is as follows:

[0101] ;

[0102] In the formula is the cumulative greenhouse gas emissions generated by the domestic waste disposal plan during the period 0-t; is a unit greenhouse gas emission function, which can be obtained by setting value points between 0 and t according to the time nodes corresponding to different management objectives in the plan, and fitting the greenhouse gas emissions generated by treating 1 ton of domestic waste and the predicted value of domestic waste generation under the corresponding value points; and Represent the estimated amount of domestic waste generated at time 0 and time t, respectively, and are set as the lower limit and upper limit of the definite integral. , we can estimate the greenhouse gas emissions generated by the management and disposal of urban domestic waste at time t in the future and screen the optimal solution for waste management and disposal.

[0103] The local garbage composition, the choice of disposal technology and the disposal target determine the classification of domestic garbage sources and the disposal structure. When the same amount of domestic garbage is treated, different carbon emissions will be generated, thus affecting the system carbon emissions in the "quality" dimension. The method provided by the present invention has local and dynamic prediction values ​​for carbon emissions from domestic garbage disposal schemes. It not only considers the influence of local factors such as garbage composition and technical characteristics at the micro level, but also can depict the spatiotemporal variation characteristics of carbon emissions from the implementation of domestic garbage disposal schemes at the macro level, so that decision makers can have a more comprehensive and objective understanding of the localized implementation effect of domestic garbage disposal schemes, as well as the improvement measures that need to be made to achieve carbon emission reduction targets in the field of garbage management.

[0104] The following is a description of the carbon emission prediction device for a bottom-up domestic waste treatment solution provided by the present invention. The bottom-up domestic waste treatment solution carbon emission prediction device described below and the bottom-up domestic waste treatment solution carbon emission prediction method described above can be referred to each other. Figure 4 As shown, the bottom-up carbon emission prediction device for domestic waste treatment scheme provided by the present invention includes the following modules:

[0105] The historical data acquisition module 410 is used to acquire a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in the target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments;

[0106] A target factor determination module 420 is used to obtain the correlation between the first historical time series and each second historical time series, and determine at least one target influencing factor from each domestic waste influencing factor based on the correlation;

[0107] The garbage quantity prediction module 430 is used to determine the second prediction time series of the target influencing factor in the target prediction period based on the second historical time series corresponding to the target influencing factor, and determine the first prediction time series based on each second prediction time series, the first prediction time series reflecting the predicted value of the amount of domestic garbage generated in the target area at each preset time in the target prediction period, and the second prediction time series reflecting the predicted value of the target influencing factor in the target area at each preset time;

[0108] The unit greenhouse gas emission prediction module 440 is used to determine the unit greenhouse gas emission at each preset time based on the garbage treatment parameters in the domestic garbage treatment plan of the target area, the domestic garbage treatment plan includes the garbage treatment parameters at each preset time, the garbage treatment parameters reflect the proportion of domestic garbage using various domestic garbage treatment methods, and the unit greenhouse gas emission is the greenhouse gas emission generated by treating a unit weight of domestic garbage;

[0109] The carbon emission prediction module 450 is used to determine the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emission.

[0110] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a bottom-up carbon emission prediction method for a domestic waste treatment scheme, the method comprising: obtaining a first historical time series and a second historical time series, the first historical time series including the values ​​of the domestic waste generation amount in a target area at multiple historical moments, the second historical time series including the values ​​of the domestic waste influencing factors in the target area at multiple historical moments; obtaining the correlation between the first historical time series and each second historical time series respectively, and determining at least one target influencing factor from each domestic waste influencing factor based on the correlation; determining a second prediction time series of the target influencing factor in a target prediction period based on the second historical time series corresponding to the target influencing factor, and determining a second prediction time series of the target influencing factor based on each second prediction time series. A first prediction time series is determined, the first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time within the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factors in the target area at each preset time; the unit greenhouse gas emissions at each preset time are determined based on the garbage disposal parameters in the domestic waste disposal plan of the target area, the domestic waste disposal plan includes the garbage disposal parameters at each preset time, the garbage disposal parameters reflect the proportion of domestic waste using various domestic waste disposal methods, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating a unit weight of domestic waste; based on the second prediction time series and the unit greenhouse gas emissions, the carbon emission prediction result of the domestic waste disposal plan is determined.

[0111] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0112] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the bottom-up carbon emission prediction method for domestic waste treatment schemes provided by the above-mentioned methods. The method includes: obtaining a first historical time series and a second historical time series, the first historical time series including the values ​​of domestic waste generation in a target area at multiple historical moments, and the second historical time series including the values ​​of domestic waste influencing factors in the target area at multiple historical moments; obtaining the correlation between the first historical time series and each second historical time series, and determining at least one target influencing factor among each domestic waste influencing factor based on the correlation; determining the target influencing factor based on the second historical time series corresponding to the target influencing factor. The first prediction time series is determined based on the second prediction time series of the target influencing factors in the target prediction period. The first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time in the target prediction period. The second prediction time series reflects the predicted value of the target influencing factors in the target area at each preset time; the unit greenhouse gas emissions at each preset time are determined based on the garbage disposal parameters in the domestic waste treatment plan of the target area. The domestic waste treatment plan includes the garbage disposal parameters at each preset time. The garbage disposal parameters reflect the proportion of domestic waste disposed of by various domestic waste disposal methods. The unit greenhouse gas emissions are the greenhouse gas emissions generated by treating unit weight of domestic waste; based on the second prediction time series and the unit greenhouse gas emissions, the carbon emission prediction result of the domestic waste treatment plan is determined.

[0113] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the bottom-up carbon emission prediction method for domestic waste treatment schemes provided by the above-mentioned methods, the method comprising: obtaining a first historical time series and a second historical time series, the first historical time series comprising the values ​​of domestic waste generation in a target area at multiple historical moments, the second historical time series comprising the values ​​of domestic waste influencing factors in the target area at multiple historical moments; obtaining the correlation between the first historical time series and each second historical time series respectively, and determining at least one target influencing factor among each domestic waste influencing factor based on the correlation; determining the target influencing factor in the target prediction period based on the second historical time series corresponding to the target influencing factor; Two prediction time series, based on each second prediction time series, determine the first prediction time series, the first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time within the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factors in the target area at each preset time; based on the garbage disposal parameters in the domestic waste treatment plan of the target area, determine the unit greenhouse gas emissions at each preset time, the domestic waste treatment plan includes the garbage disposal parameters at each preset time, the garbage disposal parameters reflect the proportion of domestic waste using various domestic waste disposal methods, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating unit weight of domestic waste; based on the second prediction time series and the unit greenhouse gas emissions, determine the carbon emission prediction result of the domestic waste treatment plan.

[0114] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A bottom-up method for predicting carbon emissions from domestic waste treatment solutions, characterized in that: The method comprises: Obtaining a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in a target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments; Obtaining the correlation between the first historical time series and each of the second historical time series, and determining at least one target influencing factor among each of the domestic waste influencing factors based on the correlation; Based on the second historical time series corresponding to the target influencing factor, determine the second prediction time series of the target influencing factor in the target prediction period, and based on each of the second prediction time series, determine the first prediction time series, the first prediction time series reflects the predicted value of the amount of domestic waste generated in the target area at each preset time in the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factor in the target area at each preset time; Determining the unit greenhouse gas emissions at each preset time based on the garbage treatment parameters in the domestic garbage treatment plan of the target area, the domestic garbage treatment plan includes the garbage treatment parameters at each preset time, the garbage treatment parameters reflect the proportion of domestic garbage disposed of by various domestic garbage disposal methods to the amount of domestic garbage generated, and the unit greenhouse gas emissions are the greenhouse gas emissions generated by treating a unit weight of domestic garbage; Based on the second prediction time series and the unit greenhouse gas emissions, the carbon emission prediction result of the domestic waste treatment solution is determined.

2. The bottom-up carbon emission prediction method for domestic waste treatment scheme according to claim 1 is characterized in that: The obtaining of the correlation between the first historical time series and each of the second historical time series includes: Grey correlation analysis is performed on the first historical time series and each of the second historical time series to obtain the correlation between the first historical time series and each of the second historical time series.

3. The bottom-up carbon emission prediction method for domestic waste treatment scheme according to claim 1 is characterized in that: The determining, based on the second historical time series corresponding to the target influencing factor, a second predicted time series of the target influencing factor in a target prediction period includes: implement The second target operation is performed to obtain the second predicted time series, and each second target operation includes the following steps: Performing an m-order accumulation operation on the current second time series to obtain a second processed time series; Predicting the next value of the last value in the second processing time series based on the second processing time series, and adding it to the second processing time series; Performing an m-order cumulative subtraction operation on the second processing time series to obtain an updated second time series; The second time series is a combination of the second historical time series and the second predicted time series. In the first second target operation, the second time series is the second historical time series. Is a positive integer.

4. The bottom-up carbon emission prediction method for domestic waste treatment scheme according to claim 3 is characterized in that: The determining the first prediction time series based on each of the second prediction time series comprises: implement The first target operation is performed to obtain the first predicted time series, and each time the first target operation is performed, the following steps are included: Performing an m-order accumulation operation on the current first time series to obtain a first processed time series; Predicting the next value of the last value in the first processing time series based on the first processing time series and the second processing time series, and adding the next value to the first processing time series; Performing an m-order cumulative subtraction operation on the first processing time series to obtain an updated first time series; The first time series is a combination of the first historical time series and the first predicted time series, and in the first first target operation, the first time series is the first historical time series.

5. The bottom-up carbon emission prediction method for domestic waste treatment scheme according to claim 4 is characterized in that: The determining, based on the second historical time series corresponding to the target influencing factor, that the target influencing factor is before the second predicted time series of the target prediction period includes: Based on multiple sample time series groups, the particle swarm algorithm is used to find the optimal solution and determine the value of m; The sample time series group includes a sample first historical time series and a sample second historical time series.

6. The bottom-up carbon emission prediction method for domestic waste treatment scheme according to claim 1 is characterized in that: The step of determining the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emission includes: Integrating the fitting function based on the amount of domestic waste processed in the second prediction time series to obtain the carbon emission prediction result; The fitting function is a function obtained by fitting the unit greenhouse gas emission corresponding to the waste treatment parameters at each preset time in the domestic waste treatment plan.

7. A bottom-up carbon emission prediction device for domestic waste treatment scheme, characterized in that: The device comprises: A historical data acquisition module, used to acquire a first historical time series and a second historical time series, wherein the first historical time series includes values ​​of the amount of domestic waste generated in a target area at multiple historical moments, and the second historical time series includes values ​​of factors affecting domestic waste in the target area at multiple historical moments; a target factor determination module, configured to obtain the correlation between the first historical time series and each of the second historical time series, and determine at least one target influencing factor from each of the domestic waste influencing factors based on the correlation; A garbage quantity prediction module, configured to determine a second prediction time series of the target influencing factor in a target prediction period based on the second historical time series corresponding to the target influencing factor, and determine a first prediction time series based on each of the second prediction time series, wherein the first prediction time series reflects the predicted value of the amount of domestic garbage generated in the target area at each preset time in the target prediction period, and the second prediction time series reflects the predicted value of the target influencing factor in the target area at each of the preset time; a unit greenhouse gas emission prediction module, for determining the unit greenhouse gas emission at each preset time based on the waste treatment parameters in the domestic waste treatment scheme of the target area, wherein the domestic waste treatment scheme includes the waste treatment parameters at each preset time, wherein the waste treatment parameters reflect the proportion of domestic waste disposed of by various domestic waste treatment methods to the domestic waste generated, and the unit greenhouse gas emission is the greenhouse gas emission generated by treating a unit weight of domestic waste; A carbon emission prediction module is used to determine the carbon emission prediction result of the domestic waste treatment solution based on the second prediction time series and the unit greenhouse gas emissions.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the bottom-up carbon emission prediction method for domestic waste treatment solutions as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the bottom-up carbon emission prediction method for domestic waste treatment solutions as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the bottom-up carbon emission prediction method for domestic waste treatment solutions as described in any one of claims 1 to 6.

Images