Park flexible resource operation method and system considering interactive carbon reduction evaluation

Abstract

The invention provides a park flexible resource operation method and system considering interactive carbon reduction evaluation. According to the implementation scheme, based on index numerical values of carbon evaluation parameters of all dimensions of a park energy system, multiple key dimension carbon evaluation parameters are obtained through screening in the carbon evaluation parameters of all the dimensions; taking the weight of each key dimension carbon evaluation parameter as an independent variable, taking the product between the index numerical value and the weight of each key dimension carbon evaluation parameter as a distinction degree, and taking distinction degree maximization as a target to construct a target function; solving the maximum value of the target function to obtain the target weight of each key dimension carbon evaluation parameter; determining a comprehensive carbon emission evaluation value based on the index numerical value and the target weight of each key dimension carbon evaluation parameter; and under the condition that the comprehensive carbon emission evaluation value does not meet the preset requirement, performing carbon reduction scheduling on the park energy system. Therefore, the accuracy of flexible resource operation scheduling of the park can be improved, and low-carbon or zero-carbon operation of the park can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission assessment, and in particular to a park flexible resource operation method and system considering interactive carbon reduction evaluation. Background Art

[0002] Commercial and office parks, due to their high energy density, complex energy systems, and diverse energy users, have become a key driver of urban energy consumption and carbon emissions. Furthermore, zero-carbon commercial and office parks, incorporating new resources such as distributed photovoltaics, energy storage, and flexible loads, face high-level operational demands, including internal energy conservation and carbon reduction, renewable energy integration, and external flexible interaction.

[0003] However, current evaluation methods for industrial park carbon emissions are typically limited to statistical or static energy efficiency analysis of direct carbon emissions. This means that the evaluation dimension of industrial park carbon emissions is single, making it difficult to drive low-carbon operation optimization. Furthermore, industrial park carbon emissions evaluations fail to fully consider the proactive regulatory effects of user-side flexible interactions on load patterns, nor do they incorporate the interactive carbon reduction benefits of flexible resources such as renewable energy consumption, energy storage charging and discharging optimization, and adjustable loads into the evaluation system. As a result, the evaluation results fail to truly reflect the contribution of flexible resource interactions to the overall carbon reduction of the industrial park. Summary of the Invention

[0004] The present invention provides a park flexible resource operation method and system considering interactive carbon reduction evaluation, which can solve at least one of the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for operating flexible resources in a park considering interactive carbon reduction evaluation, including:

[0006] Based on the index values ​​of the carbon evaluation parameters of each dimension of the park energy system, multiple key carbon evaluation parameters are screened from the carbon evaluation parameters of each dimension;

[0007] The objective function is constructed by taking the weight of each of the key dimensional carbon evaluation parameters as an independent variable, taking the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as the discrimination, and taking maximizing the discrimination as the goal;

[0008] Solving the objective function for the maximum value to obtain the target weight of each of the key dimension carbon assessment parameters;

[0009] Determine the comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension;

[0010] When the comprehensive carbon emission evaluation value does not meet the preset requirements, the park energy system is scheduled for carbon reduction.

[0011] In a second aspect, an embodiment of the present invention provides a park flexible resource operation device that considers interactive carbon reduction evaluation, including:

[0012] A screening module is used to screen the carbon evaluation parameters of each dimension based on the indicator values ​​of the carbon evaluation parameters of each dimension of the park energy system to obtain multiple key carbon evaluation parameters;

[0013] A construction module is used to construct an objective function using the weight of each of the key dimensional carbon evaluation parameters as an independent variable, the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as the discrimination, and maximizing the discrimination as the goal;

[0014] A solution module, configured to solve the objective function for a maximum value and obtain target weights of the carbon assessment parameters of each key dimension;

[0015] A determination module, configured to determine a comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension;

[0016] The scheduling module is used to perform carbon reduction scheduling on the park energy system when the comprehensive carbon emission evaluation value does not meet the preset requirements.

[0017] In the third aspect, an embodiment of the present invention also provides a park flexible resource operation system that takes into account interactive carbon reduction evaluation, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods described in the embodiments of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any one of the methods in the embodiments of the present invention.

[0019] Using the technical solution of the present invention, first, the key dimension carbon evaluation parameters are screened out from the carbon evaluation parameters of the many dimensions of the park energy system. Then, based on the weight of each key parameter, the discrimination of its index value is calculated, and then the objective function is constructed with the weight as the independent variable and the discrimination maximization as the goal. By solving the maximum value of the objective function, the target weight of the carbon evaluation parameters of each key dimension is determined. In this way, on the one hand, by screening the carbon evaluation parameters of the key dimensions, redundant information is effectively eliminated, and the evaluation focus is focused on the core factors that have a significant impact on the carbon emissions of the park, making the carbon emission assessment of the park more accurate; on the other hand, optimizing the weights guided by discrimination is conducive to a true and comprehensive reflection of the carbon emissions of the park. Based on this, combining the values ​​of each index with the target weight, the comprehensive carbon emission evaluation value of the park energy system can be calculated, thereby providing a reliable basis for carbon reduction scheduling. The final comprehensive carbon emission evaluation value can provide solid data support for carbon reduction scheduling decisions, so that carbon reduction strategies can be formulated scientifically and efficiently for the park in the future to achieve energy conservation and emission reduction goals.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present invention.

[0022] Figure 1 This is a flow chart of a park flexible resource operation method considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0023] Figure 2 This is a structural block diagram of a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of a screening module in a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0025] Figure 4 This is a structural block diagram of building modules in a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0026] Figure 5 This is a structural block diagram of a solution module in a flexible resource operation device for a park considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0027] Figure 6 This is a structural block diagram of a determination module in a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0028] Figure 7 This is a structural block diagram of a scheduling module in a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0029] Figure 8 This is a structural block diagram of a comprehensive carbon emission rating determination unit in a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention;

[0030] Figure 9 is a block diagram of an electronic device for implementing the method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following description of exemplary embodiments of the present invention is made in conjunction with the accompanying drawings, and various details of the embodiments of the present invention are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present invention. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] Figure 1 This is a flow chart of a park flexible resource operation method considering interactive carbon reduction evaluation according to an embodiment of the present invention.

[0033] like Figure 1 As shown, the park flexible resource operation method considering interactive carbon reduction evaluation may include:

[0034] S110, based on the indicator values ​​of the carbon evaluation parameters of each dimension of the park energy system, screening the carbon evaluation parameters of each dimension to obtain multiple key carbon evaluation parameters;

[0035] S120, constructing an objective function with the weight of each key dimension carbon evaluation parameter as an independent variable, the product of the index value of each key dimension carbon evaluation parameter and the weight as the discrimination, and maximizing the discrimination as the goal;

[0036] S130, solving the maximum value of the objective function to obtain the target weight of each key dimension carbon assessment parameter;

[0037] S140: Determine the comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension;

[0038] S150: When the comprehensive carbon emission evaluation value does not meet the preset requirements, the park energy system will be scheduled for carbon reduction.

[0039] In an embodiment of the present invention, the carbon evaluation parameters of multiple dimensions in the park energy system are screened to obtain multiple key dimensional carbon evaluation parameters. The discrimination of the index values ​​of the carbon evaluation parameters of each key dimensional carbon evaluation parameter is calculated by the weight of each key dimensional carbon evaluation parameter. The weight of each key dimensional carbon evaluation parameter is used as an independent variable, and an objective function is established with the goal of maximizing the discrimination. By solving the maximum value of the objective function, the target weight of each key dimensional carbon evaluation parameter is obtained. By screening the key dimensional carbon evaluation parameters, redundant information can be eliminated from the multiple dimensional carbon evaluation parameters, focusing on the core factors that have a significant impact on the carbon emissions of the park energy system, avoiding interference from secondary factors, and making the evaluation more targeted. In this way, the comprehensive carbon emission evaluation value of the park energy system can be calculated based on the values ​​of each indicator and its corresponding target weight, thereby improving the reliability of the carbon reduction scheduling of the park energy system.

[0040] For example, the carbon evaluation parameters of each dimension are also indicators of different dimensions. There are indicators of multiple dimensions in the park energy system, such as energy dimension, carbon emission dimension, and flexible resource dimension. Each type of indicator can be further refined into multiple indicators. The rich indicator dimensions are conducive to ensuring that the park achieves maximum energy saving and carbon reduction effects while optimizing the energy structure.

[0041] For example, the indicator values, i.e., the values ​​of each indicator calculated based on the corresponding calculation method, are used to provide a data basis for carbon emission scheduling and park rating.

[0042] According to the above implementation method, first, based on the index values ​​of the carbon evaluation parameters of each dimension of the park energy system, multiple key dimension carbon evaluation parameters are screened out. Then, the weights of these key dimension carbon evaluation parameters are set as independent variables, and the product of the index value and the weight is used as the discrimination, to construct an objective function that maximizes the discrimination. After solving the function to obtain the target weight, the comprehensive carbon emission evaluation value of the park energy system is calculated in combination with the index value. If the evaluation value does not meet the preset requirements, carbon reduction scheduling will be carried out on the park energy system. In this way, by screening key parameters, the core factors can be accurately focused on and redundant interference can be reduced; with the goal of maximizing discrimination, a function is constructed to solve the weights to ensure that the weight setting is scientific and reasonable. In addition, the comprehensive evaluation value is linked with the carbon reduction scheduling, which can not only quantitatively evaluate the carbon emission level of the park, but also make timely adjustments to the deficiencies, providing a systematic and practical solution for efficient carbon reduction and optimized energy management in the park.

[0043] In one embodiment, based on the index values ​​of the carbon evaluation parameters of each dimension of the park energy system, multiple key dimensional carbon evaluation parameters are screened from the carbon evaluation parameters of each dimension, including: determining the index cumulative contribution rate of the carbon evaluation parameters of each dimension based on the index values ​​of the carbon evaluation parameters of each dimension; when the index cumulative contribution rate is greater than the preset cumulative contribution rate threshold, adding the corresponding dimensional carbon evaluation parameter to the high contribution rate parameter set; performing independence calculations on the carbon evaluation parameters of each dimension in the high contribution rate parameter set, and screening the parameters in the high contribution rate parameter set based on the independence scores of the carbon evaluation parameters of each dimension to obtain a high independence parameter set; sorting the independence scores of the carbon evaluation parameters of each dimension in the high independence parameter set in descending order, and taking the first K dimensional carbon evaluation parameters as the key dimensional carbon evaluation parameters; wherein, the ratio between the sum of the variances of the index values ​​of the first K dimensional carbon evaluation parameters and the sum of the variances of the index values ​​of the carbon evaluation parameters of each dimension in the high independence parameter set is greater than or equal to the first threshold, and K is less than or equal to the second threshold, and the first threshold is less than the second threshold.

[0044] For example, the carbon evaluation parameters for each dimension of a park energy system include park energy management and control evaluation parameters, park carbon emission management and control evaluation parameters, and park flexibility management and control evaluation parameters. Each of these carbon evaluation parameters can be further divided into multiple carbon evaluation parameters based on overall performance indicators and sub-item performance indicators. The specific calculation results of each carbon evaluation parameter are the indicator values ​​for each dimension of the park energy system.

[0045] In this example, the overall effectiveness indicator parameters in the park energy management and control evaluation parameters include the park energy consumption intensity, the park energy conservation rate, and the renewable energy utilization rate; its sub-item effectiveness indicator parameters include the park sub-item energy consumption intensity and the park sub-item energy conservation rate. The overall effectiveness indicator parameters in the park carbon emission management and control evaluation parameters include the park carbon emission intensity, the park carbon reduction rate, and the park carbon offset rate; its sub-item effectiveness indicator parameters include the park building carbon emissions, the park municipal carbon emissions, the park transportation carbon emissions, and the park's other carbon emissions. The overall effectiveness indicator parameters in the park flexible management and control evaluation parameters include the park response time and adjustment power; its sub-item effectiveness indicator parameters include the flexible interactive carbon reduction benefit and the renewable energy absorption benefit.

[0046] Exemplarily, in the park energy system, the park flexibility management and control evaluation parameters can be set as short-cycle indicators, and the park energy management and control evaluation parameters and related indicators in the park carbon emission management and control evaluation parameters can be set as long-cycle indicators. For example, the park energy consumption in the park energy management and control evaluation parameters can be set as a long-cycle indicator. In addition, a periodic drift and dynamic adjustment mechanism can also be set in the park energy system. The periodic drift and dynamic adjustment mechanism can adapt to the periodic hierarchical changes of different indicators such as park flexibility management (short cycle), energy management and carbon emission control (long cycle). In order to achieve dynamic reconstruction of the indicator operation status under abnormal conditions such as sudden changes in carbon emissions and fluctuations in energy consumption, improve the adaptability and precision of the evaluation indicators, and assist the park in precise carbon reduction and coordinated optimization. For example, if a long-cycle indicator (such as annual carbon emission intensity) fluctuates abnormally in a short cycle (such as a surge in hourly carbon intensity), the system will trigger the "periodic dimension reduction migration" of the indicator, migrating it from the long-cycle tracking state to the short-cycle dynamic tracking state.

[0047] Exemplarily, the carbon evaluation parameters of each dimension are calculated through the preset physical boundaries to obtain the index values ​​of the carbon evaluation parameters of each dimension. The physical boundaries include all buildings, energy systems, transportation facilities, etc. within the park. Specifically, the carbon emission calculation boundaries within the park include: the energy consumption of all buildings in the park (such as the power demand of HVAC, lighting, domestic hot water, sockets, cooking equipment, etc.); the operating energy consumption of the park's municipal, transportation and other facilities; direct and indirect carbon emissions within the park; the use of renewable energy and its efficiency, and renewable energy outside the park but only supplying energy to the park is also included in the calculation. The contribution of carbon sinks and carbon offset measures within the park to the overall carbon balance is also included in the evaluation scope.

[0048] It should be noted that the carbon emissions of electric vehicles, if they are non-traveling vehicles within the park or provide energy for the park, need to be included in the park's carbon emissions calculations; if they are passing vehicles, they will not be included in the park's building carbon emissions.

[0049] For example, the overall effectiveness index parameters in the park energy management and control evaluation parameters measure the park and the park's energy consumption from indicators such as the park and the park's energy consumption intensity, comprehensive energy saving rate, and renewable energy utilization rate.

[0050] The calculation formula for the park's energy consumption intensity is as follows:

[0051]

[0052] Where: E is the energy consumption intensity of the park; E E is the comprehensive energy consumption value of the park excluding renewable energy power generation; A is the building area of ​​the park with buildings as the main body. If there are other carbon emission activity areas, the corresponding area will be counted; f i is the energy conversion coefficient of type i energy; Er,i E is the annual electricity generation of type i renewable energy; rd,i is the amount of electricity generated by type i renewable energy in the year.

[0053] The calculation formula for the park's comprehensive energy-saving rate is as follows:

[0054]

[0055] Where: η p E is the comprehensive energy saving rate of the park; D is the energy consumption intensity value of the designed park; E R is the energy intensity value of the benchmark park.

[0056] The formula for calculating the renewable energy utilization rate is as follows:

[0057]

[0058] Where: REP p is the utilization rate of renewable energy; EP h EP is the amount of renewable energy used in the heating system; c is the amount of renewable energy used in the air-conditioning system; EP w is the amount of renewable energy used in domestic hot water systems; Q h is the annual heat consumption for heating; Q c Q is the annual cooling consumption; w E is the annual domestic hot water heat consumption; l is the energy consumption of the lighting system; E e This is the energy consumption of other equipment in the park.

[0059] For example, the sub-item performance indicator parameters in the park energy management and control evaluation parameters include all sources related to the park's operating energy consumption, among which the park's sub-item energy consumption intensity and the park's sub-item energy saving rate are the core.

[0060] The calculation formula for the park's sub-item energy saving rate is as follows:

[0061]

[0062] Where: η p E is the energy saving rate of the park; Di E is the energy consumption value of the sub-item design park; Ri It is the energy consumption intensity value of the sub-item benchmark park.

[0063] The calculation formula for the energy consumption intensity of each item in the park is as follows:

[0064]

[0065] Where: E is the energy consumption intensity of the park; Ei is the amount of electricity generated by renewable energy of type i; f i is the energy conversion coefficient of type i energy; A is the building area of ​​the park with buildings as the main body.

[0066] For example, the overall effectiveness evaluation parameters in the park carbon emission control evaluation parameters include the park carbon emission intensity, the park carbon reduction rate, and the park carbon offset rate.

[0067] The calculation formula for the park’s carbon emission intensity is as follows:

[0068]

[0069] Where: C D is the regional carbon emissions; C d,b is the building carbon emissions; C d,t is the carbon emissions from transportation; C d,m is municipal carbon emissions; C d,o Carbon emissions from other energy consumption; C d,r Carbon reduction for renewable energy power generation; C d,s is the carbon reduction amount of regional carbon sink; C d,e is the carbon emissions generated by energy transported outside the region; A is the total building area of ​​the commercial and office park.

[0070] The calculation formula for the park’s carbon reduction rate is as follows:

[0071]

[0072] Where: η p is the carbon reduction rate of the park; C D is the carbon emission intensity of the evaluated park; C R is the carbon emission intensity of the benchmark park.

[0073] The calculation formula for the park’s carbon offset rate is as follows:

[0074]

[0075] Where: R credit is the carbon offset rate; C R is the carbon emission intensity of the benchmark park; cc is the total amount of carbon credit products; A is the total building area of ​​the park.

[0076] For example, the sub-item effectiveness evaluation parameters in the park carbon emission control evaluation parameters include park building carbon emissions, park municipal carbon emissions, park transportation carbon emissions, and park other carbon emissions.

[0077] The calculation formula for park building carbon emissions is as follows:

[0078]

[0079] Where: C d,b is the building carbon emissions; C E,i is the carbon emission intensity of the i-th building; A b,i is the area of ​​the i-th building; i is the i-th building in the area.

[0080] Among them, the park's municipal carbon emissions should include carbon emissions from waste treatment, municipal water supply and drainage systems, and municipal lighting. The calculation formula is as follows:

[0081] C d,m =C d,m1 +C d,m2 +C d,m3 ;

[0082] Where: C d,m is municipal carbon emissions; C d,m1 Carbon emissions for waste treatment; C d,m2 Carbon emissions from the park’s water supply and drainage system; C d,m3 Carbon emissions for municipal lighting.

[0083] The carbon emissions from transportation within the park should include the carbon emissions from transportation activities within the physical area of ​​the area, but not the carbon emissions from vehicles passing through. The carbon emissions index for transportation within the park is calculated as follows:

[0084]

[0085] Where: L i,j D is the total annual mileage of the jth vehicle among vehicles using the i-th energy source; i,j EF is the annual average energy consumption per unit mileage of the jth vehicle in the i-th energy vehicle; i is the carbon emission factor of the i-th energy; i is the energy type number; j is the vehicle number.

[0086] The calculation formula for other carbon emissions in the park is as follows:

[0087]

[0088] Where C d,o Carbon emissions generated by other energy consumption in the park; i is the annual energy consumption of the i-th category of energy consumption; EF i is the carbon emission factor of the i-th energy source.

[0089] For example, the overall effectiveness indicator parameters in the park flexible management and control evaluation parameters include park response time and adjustment power.

[0090] The park response time calculation formula is as follows:

[0091]

[0092] Where, T eff is the park response time; ΔP(t) is the load power adjustment amount at time t during the park's flexible response period, that is, the absolute value of the difference between the actual power after adjustment and the reference power; ΔP tar (t) is the target value of the power regulation at time t, that is, the absolute value of the difference between the reference power and the target power; t0 is the starting time of flexible response or regulation; t end is the end time of flexible response or adjustment; dt is the time step. According to the flexible response characteristics, time intervals of different sizes such as h, min, s, etc. can be selected as the step.

[0093] Among them, when the park participates in the real-time flexible response process, the adjustment power calculation formula is as follows:

[0094] △P dr (t) = P fle (t)-P ref (t);

[0095] Where, △P dr (t) is the regulated power; P fle (t) is the actual load power of the park participating in the flexible response at time t; P ref (t) is the baseline power at time t when the park does not participate in flexible response.

[0096] For example, the sub-item performance indicator parameters in the park's flexible management and control evaluation parameters include flexible interactive carbon reduction benefits and renewable energy absorption benefits.

[0097] The calculation formula for flexible interactive carbon reduction benefits is as follows:

[0098]

[0099] In the formula, BI c is the carbon reduction benefit during the flexible response period; C fle is the total carbon emissions of the park during the flexible response and subsequent rebound process; C ref is the total carbon emissions of the park under the baseline operating conditions (not participating in flexible response).

[0100] The calculation formula for renewable energy consumption benefits during the flexible response period is as follows:

[0101]

[0102] In the formula, BI res For the benefit of renewable energy consumption; RES fleRES refers to the amount of renewable energy consumed during the response period and subsequent recovery period when the park participates in flexible regulation; ref It refers to the amount of renewable energy absorbed during the response period and subsequent recovery period when the park does not participate in flexible regulation.

[0103] For example, due to the different dimensions of the indicator values ​​in the carbon evaluation parameters of each dimension, the evaluation scale will be inconsistent, which will affect the evaluation results. Therefore, the indicator values ​​must be standardized to obtain standardized indicator values ​​of the carbon evaluation parameters of each dimension.

[0104] The function expression of the standardization process is as follows:

[0105]

[0106] Where x′ ij is the standardized index value of the jth indicator of the carbon evaluation parameter of the i-th dimension after standardization; x ij is the original index value of the jth index of the carbon evaluation parameter of the i-th dimension; min 1≤i≤n (x ij ) is the minimum value of the carbon evaluation parameter index of n dimensions under the jth index; max 1≤i≤n (x ij ) is the maximum value of the carbon evaluation parameter index in n dimensions under the j-th indicator.

[0107] For example, the coefficient of dispersion is calculated for the standardized index values ​​of each carbon assessment parameter dimension to obtain the coefficient of dispersion for each dimension. Based on the coefficient of dispersion for each carbon assessment parameter dimension, the cumulative contribution rate of the indicator for each carbon assessment parameter dimension is determined. Determining the cumulative contribution rate based on the coefficient of dispersion can highlight parameters with large fluctuations and significant impact on overall characteristics, facilitating the selection of key carbon assessment parameters.

[0108] The calculation expression of the dispersion coefficient is as follows:

[0109]

[0110] Where c j is the dispersion coefficient of carbon evaluation parameter j; σ j is the standard deviation of carbon evaluation parameter j; μ j is the mean value of carbon evaluation parameter j.

[0111] The calculation expression for the cumulative contribution rate of the carbon assessment parameters in each dimension is as follows:

[0112]

[0113] Where g lis the cumulative contribution rate of the carbon evaluation parameters in each dimension; c′ j is the dispersion coefficient of the first l carbon evaluation parameters with the largest dispersion coefficient; m is the total number of carbon evaluation parameters.

[0114] For example, when the cumulative contribution rate of an indicator exceeds a preset cumulative contribution rate threshold (for example, the cumulative contribution rate threshold is preset to 85%), the dimensional carbon evaluation parameter corresponding to the indicator is included in the high contribution rate parameter set. This provides a more reliable basis for the subsequent precise screening of key dimensional carbon evaluation parameters with high contributions to carbon evaluation, and improves the accuracy and effectiveness of carbon reduction scheduling in the park energy system.

[0115] For example, after initially screening the carbon assessment parameters of each dimension based on the cumulative contribution rate of the indicators, a secondary screening can be performed using the indicator independence. The independence of the indicators is reflected by the correlation coefficient. The smaller the indicator correlation coefficient, the higher the indicator independence.

[0116] In this example, the high-contribution parameter set includes multiple carbon assessment parameters. By performing independence calculations on each of these parameters, we can obtain the independence scores for each of these parameters. Based on these independence scores, we filter parameters from the high-contribution parameter set to obtain a high-independence parameter set. Further filtering out the high-independence parameter set from the high-contribution parameter set constitutes a secondary optimization of the parameters. The high-independence parameter set can more accurately reflect the carbon emission characteristics of different dimensions, facilitating the subsequent development of targeted emission reduction and carbon optimization measures, thereby improving resource utilization efficiency.

[0117] The calculation expressions for the independence scores of carbon assessment parameters in each dimension are as follows:

[0118]

[0119] Where r pq is the correlation coefficient between the carbon assessment parameters of the pth and qth dimensions; x kp is the kth indicator value of the carbon evaluation parameter of the pth dimension, and are the mean values ​​of the carbon assessment parameter indicators of the pth and qth dimensions respectively.

[0120]

[0121] Where, t p is the sum of the absolute values ​​of the correlation coefficients between the carbon evaluation parameter of the p-th dimension and all the remaining m-dimensional carbon evaluation parameters (q traverses from 1 to m); d p is the independence score of the p-th dimension carbon evaluation parameter; m is the total number of dimensional carbon evaluation parameters.

[0122] For example, after obtaining a set of highly independent parameters through the aforementioned calculations, the independence scores of the carbon assessment parameters for each dimension are sorted in descending order, and the top K dimensional carbon assessment parameters are selected as the key dimensional carbon assessment parameters. This sorting by independence score prioritizes parameters that contribute significantly to the carbon assessment and are independent of each other, avoiding the inclusion of duplicate indicators with strong correlations. For example, if "energy consumption" and "carbon emission intensity" are highly correlated, only the parameters with the higher independence scores need to be retained, thereby reducing data redundancy and computational complexity.

[0123] In this example, the value of K must satisfy the following conditions: the ratio of the sum of the variances of the index values ​​of the first K dimensional carbon assessment parameters to the sum of the variances of the index values ​​of the dimensional carbon assessment parameters in the high independence parameter set is greater than or equal to a first threshold, and K is less than or equal to a second threshold, where the first threshold is less than the second threshold. For example, the first threshold can be 80%, and the second threshold can be the product of the number of dimensional carbon assessment parameters and 40%.

[0124] In one embodiment, the weight of each key dimension carbon evaluation parameter is used as an independent variable, the product of the index value of each key dimension carbon evaluation parameter and the weight is used as the discrimination, and the goal is to maximize the discrimination, thereby constructing an objective function, including: multiplying the weight of each key dimension carbon evaluation parameter by its respective index value to obtain the contribution value of each key dimension carbon evaluation parameter; calculating the mean of the contribution value of each key dimension carbon evaluation parameter to obtain the contribution average value; determining the discrimination based on the sum of the squares of the differences between the contribution value of each key dimension carbon evaluation parameter and the contribution average value; and constructing an objective function with the weight of each key dimension carbon evaluation parameter as an independent variable and the goal is to maximize the discrimination.

[0125] For example, there are multiple carbon evaluation parameters in the park energy system. After the above steps, multiple key carbon evaluation parameters are selected to measure the flexible interactive carbon reduction capability of the park. Each key carbon evaluation parameter can be calculated according to its corresponding calculation expression to obtain an index value. The index value of the i-th key carbon evaluation parameter is x i (i=1, 2, ..., n), x i The corresponding weight is w i . All weights are non-negative and satisfy the normalization constraints:

[0126]

[0127] Normalization conditions ensure that weights can be reasonably allocated so that comprehensive comparisons can be made after weighting the evaluation parameters of each key carbon dimension. The calculation expression for the contribution value of each key dimension carbon evaluation parameter is as follows:

[0128]

[0129] In the formula, S represents the contribution value of the key carbon dimension evaluation parameter, which is also the park's comprehensive evaluation score. This comprehensive score S represents the overall level of a single park's flexible interactive carbon reduction capabilities. However, to make the evaluation results more prominent among the evaluation parameters of different key carbon dimensions, this example does not focus solely on the numerical value of S. Instead, it focuses on maximizing the difference between the weighted scores of the evaluation parameters of each key carbon dimension by optimizing the weights, thereby improving the discrimination of the comprehensive evaluation.

[0130] For example, in order to quantitatively describe the degree of difference between the weighted scores of the evaluation parameters of each key carbon dimension, the discrimination index D is introduced as the objective function.

[0131] First, define the weighted score of the carbon assessment parameter of the i-th key dimension as:

[0132] y i =w i x i ,i=1,2,…,n;

[0133] Where y i It represents the contribution value of carbon evaluation parameters in each key dimension, that is, the contribution value of each indicator to the comprehensive evaluation.

[0134] Secondly, use each y i The degree of dispersion is used to measure the discrimination. Preferably, the variance of the weighted score is used as the measure of the difference. For the convenience of calculation, the calculation expression of the contribution average is as follows:

[0135]

[0136] Where, Indicates the average contribution value of carbon assessment parameters in key dimensions.

[0137] Finally, the sum of the squares of the differences between the contribution values ​​of the carbon evaluation parameters of each key dimension and the average contribution value is used as the discrimination. The objective function is constructed with the weights of the carbon evaluation parameters of each key dimension as independent variables and the goal of maximizing the discrimination. The expression of the objective function D is as follows:

[0138]

[0139] Where W is the weight vector. The larger the value of D(W), the more significant the difference between the weighted scores of the carbon assessment parameters in each key dimension, and the higher the discrimination of the comprehensive evaluation. The optimization goal is to find the optimal weight vector (the optimal weight is also the target weight) to maximize the discrimination D(W) while satisfying the weight normalization constraint. The corresponding expression is as follows:

[0140]

[0141] In this example, by maximizing the above objective function, the differences in carbon evaluation parameters of key dimensions within a single park can be significantly amplified, making the comprehensive evaluation results more recognizable and highlighting the strengths and weaknesses of the park in carbon evaluation parameters of different dimensions.

[0142] According to the above implementation, based on the contribution value of each key dimension carbon evaluation parameter, the contribution values ​​of all key dimension carbon evaluation parameters are averaged to obtain the contribution average value. Then, the sum of the squares of the difference between the contribution value of each key dimension carbon evaluation parameter and the contribution average value is calculated to determine the discrimination of the parameter. Finally, the weight of the key dimension carbon evaluation parameter is used as the independent variable, and the optimization goal is to maximize the discrimination, and construct the corresponding objective function. By quantitatively analyzing the key dimension carbon evaluation parameters, the importance of each parameter in the carbon evaluation can be more accurately measured. Constructing a function with the goal of maximizing discrimination can further highlight the differences between different parameters, help screen out the carbon evaluation parameters that really have a significant impact on the carbon evaluation results, and make the carbon reduction scheduling of the park energy system more scientific and accurate.

[0143] In one embodiment, the maximum value of the objective function is solved to obtain the target weights of the carbon evaluation parameters of each key dimension, including: initializing the population, wherein the population includes multiple individuals, each individual corresponds to a candidate weight vector, and the candidate weight vector includes the weights of the carbon evaluation parameters of each key dimension; based on the objective function, the discrimination degree of the candidate weight vector corresponding to each individual in the population of this iteration is calculated to obtain the discrimination degree of each individual in the population of this iteration; when the highest discrimination degree of each individual in the population of this iteration does not meet the preset conditions, the discrimination degree of each individual in the population of this iteration is calculated based on the discrimination degree of each individual in the population of this iteration and the discrimination degree of each individual in the population of this iteration. The selection probability of each individual in the population of this iteration is determined by the ratio of the sum of the discrimination degrees; according to the selection probability of each individual in the population of this iteration, individuals are screened in the population of this iteration to obtain the parent population; parent individuals are randomly selected from the parent population for pairing to obtain parent individual pairs; based on the random crossover coefficient, the candidate weight vectors corresponding to the parent individual pairs are cross-calculated to obtain multiple offspring individuals, and the multiple offspring individuals are used as the population of the next iteration; the iteration is stopped when the highest discrimination meets the preset conditions, and the candidate weight vectors corresponding to the individuals corresponding to the highest discrimination are used to determine the target weights of the carbon assessment parameters of each key dimension.

[0144] For example, the population includes multiple individuals, and during initialization, multiple non-negative real numbers are randomly generated as weights for each individual in the population. i =1, the multiple non-negative real numbers need to be normalized, where wi is the weight of the carbon assessment parameter of the i-th key dimension.

[0145] For example, the population obtained after initialization contains multiple candidate weight vectors. The process of obtaining the candidate weights corresponding to each individual in the population when initializing the population can be abstracted into the following function expression:

[0146]

[0147] in, is the weight of the carbon assessment parameter of the i-th key dimension after normalization; v i is the i-th non-negative real number randomly generated during the initialization process, used to construct the weight; n is a randomly generated non-negative real number v i The number of .

[0148] For example, the objective function is defined as the fitness function of the genetic algorithm, which is used to evaluate the quality of each individual in the population. A discrimination calculation is performed on the candidate weight vectors corresponding to each individual in the population of this iteration to obtain the discrimination of each individual in the population of this iteration. Based on the discrimination of each individual in the population of this iteration, the fitness of each individual in the population of this iteration is determined.

[0149] In this example, the expression for discrimination calculation is as follows:

[0150]

[0151] Among them, D(W (k) ) is the discrimination of the kth individual; f(W (k) ) is the fitness of the kth individual; W(k) is the kth individual, that is, the kth group weight vector; is the weight of the carbon assessment parameter of the i-th key dimension in the k-th individual (k-th group of weight vector); is the weight of the j-th key dimension carbon assessment parameter in the k-th individual (k-th group weight vector); x i is the index value of the carbon evaluation parameter of the i-th key dimension; x j is the index value of the j-th key dimension carbon evaluation parameter; n is the number of key dimension carbon evaluation parameters.

[0152] In this example, f(W (k) ) value, the greater the difference in the weighted scores of the carbon assessment parameters in each key dimension under that set of weights, that is, the higher the individual's fitness. In each iteration, the algorithm selects individuals with better performance based on their fitness value to transfer the weight gene.

[0153] For example, the fitness values ​​of the carbon evaluation parameters of each key dimension can be obtained based on the above calculations. Individuals in the population are selected according to the fitness values, and sub-individuals with high fitness are given a greater probability of being passed on to the next generation. When the highest discrimination among the discriminations of the individuals in the population of this iteration does not meet the preset conditions, the selection probability of each individual in the population of this iteration is determined based on the ratio between the discrimination of each individual in the population of this iteration and the sum of the discriminations of each individual in the population of this iteration. Through the selection operation, excellent weight combinations will be more likely to be inherited by the next generation, while combinations with low fitness will be eliminated.

[0154] In this example, the calculation expression for the selection probability of each individual in the population of this iteration is as follows:

[0155]

[0156] Among them, p k is the selection probability of each individual in the population; N is the population size, which can be N = 5n-10n; f(W (k) ) is the fitness of the kth individual; f(W (m) ) is the fitness of the mth individual.

[0157] Exemplarily, based on the selection probability calculation for each individual in the population of this iteration, after obtaining the selection probability of each individual, multiple individuals corresponding to larger selection probabilities are screened from the selection probabilities of each individual as parent individuals, and the multiple parent individuals obtained are used as the parent population.

[0158] For example, randomly selected parent individuals from the parent population are paired to obtain parent individual pairs, and real number crossover is performed on the candidate weight vectors corresponding to the parent individual pairs to generate multiple new offspring individuals. When real number crossover is used, one or more crossover points can be randomly generated for each pair of parent individuals. Through the crossover operation, a new weight combination scheme is generated. After crossover, the candidate weight vectors corresponding to the offspring individuals need to be normalized again. Therefore, in order to ensure weights and constraints, the arithmetic crossover method is used to generate offspring. For the i-th weight, offspring 1 and offspring 2 can be generated as follows:

[0159]

[0160] in, is offspring 1; is the offspring 2; α is a crossover coefficient randomly generated within [0, 1]; is the parent individual a; is the parent individual b.

[0161] This generates the next generation of candidate weighted populations. This new population is then iterated repeatedly to continuously evolve the weight combinations. The iterative update cycle ends when a preset termination condition is reached. This termination condition can be a criterion such as reaching the maximum number of iterations or the maximum fitness increase falling below a threshold over several consecutive generations. When the termination condition is met, the genetic algorithm iteration ends, and the candidate weight vector corresponding to the individual with the highest fitness value in the population becomes the target weight.

[0162] According to the above implementation, the iterative optimization of a genetic algorithm automatically searches for the optimal weighted combination of carbon assessment parameters across key dimensions. By using discrimination to screen individuals, it effectively retains advantageous weights and eliminates disadvantageous weights, thereby gradually approaching the optimal solution. This entire process is efficient and systematic, enabling a more scientific and rational determination of carbon assessment parameter weights, providing strong support for carbon emission assessments and the development of carbon reduction strategies.

[0163] In one embodiment, based on the index values ​​and target weights of the carbon evaluation parameters of each key dimension, the comprehensive carbon emission evaluation value of the park energy system is determined, including: multiplying the index values ​​of the carbon evaluation parameters of each key dimension by their respective target weights to obtain the carbon emission evaluation values ​​of the carbon evaluation parameters of each key dimension; summing up the various carbon emission evaluation values ​​to obtain the comprehensive carbon emission evaluation value of the park energy system.

[0164] For example, the calculation expression of the comprehensive carbon emission evaluation value can be:

[0165] Y c =α1×W1+α2×W2+…+α m ×W m ;

[0166] Among them, Y c is the comprehensive carbon emission evaluation value; α1 is the index value of the carbon evaluation parameter of the first key dimension; W1 is the target weight corresponding to the index value of the carbon evaluation parameter of the first key dimension; α2 is the index value of the carbon evaluation parameter of the second key dimension; W2 is the target weight corresponding to the index value of the carbon evaluation parameter of the second key dimension; α m is the index value of the carbon evaluation parameter of the mth key dimension; W m is the target weight corresponding to the indicator value of the carbon assessment parameter of the mth key dimension.

[0167] According to the above implementation, since different parameters vary in nature and impact, each key carbon assessment parameter is assigned a corresponding target weight, which can scientifically quantify the contribution of each factor to carbon emissions. For example, the proportion of carbon emissions from park buildings in the park's flexible management and control evaluation parameters has a significant impact on the park's rating, so it is assigned a higher weight. By multiplying the two together to calculate the carbon emission evaluation value, it can reasonably highlight its role in the park's overall carbon emissions.

[0168] In one embodiment, a park energy system is scheduled for carbon reduction, including: determining a comprehensive carbon emission rating of the park energy system based on carbon evaluation parameters of each key dimension of the park energy system; determining a reward function of an intelligent agent based on the comprehensive carbon emission rating of the park energy system and the carbon evaluation parameters of each key dimension; constructing a state space of the intelligent agent through the operating environment data of the park energy system, and constructing an action space of the intelligent agent based on the output power of each flexible resource of the park energy system at each time; using an intelligent agent, sampling action individuals from the action space and the state space for interactive learning, and calculating the interactive learning results based on the reward function to obtain a reward value for each action individual, and using the action individual with the largest output reward value as the carbon reduction scheduling plan for the park energy system, wherein the carbon reduction scheduling plan for the park energy system includes the target output power of each flexible resource at each time.

[0169] For example, the function expression of the agent's reward function R is as follows:

[0170] R=w C ·C t +w E ·E t +w S ·S t +w F ·F t -w M ·M t ;

[0171] Among them, w C is the weight coefficient corresponding to the carbon emission reduction; w E is the weight coefficient corresponding to the energy efficiency improvement; w S is the weight coefficient corresponding to the comfort maintenance index; w F w is the weight coefficient corresponding to the load peak shaving effect of the comfort maintenance index; M is the weight coefficient corresponding to the economic cost of regulation; C t is the reduction in carbon emissions; Et is the improvement in energy efficiency; S t Maintains comfort level; F t Maintain the load peak reduction effect (such as peak load reduction ratio) for comfort; M tTo regulate economic costs, the agent can achieve a balance between different control objectives by integrating multiple factors such as carbon emission reduction, peak-valley reduction, economic costs, and user comfort into the reward function and assigning appropriate weights.

[0172] For example, a state vector composed of key carbon evaluation parameters (energy management evaluation parameters, carbon emission management evaluation parameters, and flexible management indicator evaluation parameters) is used as the input to the multi-agent reinforcement learning environment state, enabling the agents to fully perceive the current system operating conditions and carbon performance, providing a basis for decision-making. This state vector includes information such as the park's photovoltaic output, energy storage capacity, indoor temperature requirements, load levels, and the grid's carbon factor, accurately reflecting the dynamic characteristics of the park's energy system.

[0173] For example, a complete state space is constructed using building and equipment information provided by the campus Building Information Model (BIM). The BIM model includes the spatial topology of the campus buildings, thermal parameters of the building envelope, equipment rated performance and energy efficiency parameters, and historical and real-time energy usage data. Based on this data, future load and renewable energy output can be predicted (such as building cooling and heating loads and photovoltaic power generation), and this information can be perceived as part of the state by the intelligent agent.

[0174] For example, the state vector includes the room temperature and setpoint temperature for each zone, air conditioning COP efficiency, energy storage state of charge, current and projected photovoltaic output, electric vehicle charging requirements, and the grid's carbon emission factor for the current period. Spatial topology information is used to clarify the correspondence and mutual influence between flexible resources and building zones, thereby enhancing the agent's perception of complex building environments. Therefore, with improved BIM data, the agent can obtain a more comprehensive and accurate understanding of the environmental state, providing a basis for decision-making on carbon reduction scheduling.

[0175] For example, corresponding action spaces can be constructed for various flexible resources. For example, the action space of an air conditioner can be defined as adjusting the temperature setpoint or fan power, turning on / off the refrigeration compressor, etc.; the action space of an energy storage system includes charging and discharging power settings; the action space of a photovoltaic module includes output regulation or power limit settings; and the electric vehicle charging pile module controls charging / discharging power or charging schedules. The equipment performance curves and operating constraints provided by BIM data can be used to define the boundaries of the action space (for example, limiting the control command amplitude based on the equipment's rated power and efficiency), ensuring that action decisions are within the physically feasible range.

[0176] For example, the agent selects individual actions from the action space, interacts with the state space for learning, calculates the reward value of each individual action through a reward function, and determines the action individual with the highest reward value as the carbon reduction scheduling plan for the park's energy system, clarifying the target output power of each flexible resource at different time periods. In this way, first, the agent can flexibly adjust the scheduling strategy based on the real-time state changes of the energy system, effectively responding to uncertainties such as fluctuations in renewable energy generation and load changes; second, through the reward function, it comprehensively considers multiple objectives such as carbon emissions, operating costs, and power balance, avoiding local optimality and maximizing overall benefits; third, through continuous interaction, it continuously optimizes the strategy, improves the accuracy and reliability of the scheduling plan, and provides strong support for the low-carbon and efficient operation of the park.

[0177] For example, the agents can adopt a layered architecture (high-level and low-level agents), where the high-level and low-level agents achieve joint optimization through a collaborative reward function and communication mechanism. The high-level agent continuously observes global performance indicators (such as campus energy management, campus carbon emission management, and campus flexibility management) to adjust the macro strategy, while the low-level agents fine-tune the local execution to meet the high-level goals.

[0178] In this example, the state of the high-level agent encompasses information about the entire campus (provided by the fusion of BIM and real-time data), the operational status of flexible resources, and the actual operating values ​​of various indicators. Therefore, the high-level agent formulates resource allocation plans and response priority strategies from a global perspective. Simultaneously, the high-level agent generates macro-control instructions or reference values ​​for various underlying resources, such as how many kilowatts the energy storage system should output to support the load at the current moment, how much load the air conditioning system should reduce overall, whether photovoltaic power generation should be prioritized for self-use or export, and whether charging time for electric vehicle fleets should be delayed.

[0179] In this example, each flexible resource at the bottom level corresponds to an execution agent, which implements the device control operations directed by the higher-level agent. For example, the air conditioning agent senses the real-time temperature, humidity, and occupancy of the area, as well as the current operating mode and efficiency of the air conditioning equipment; the energy storage agent senses the battery state of charge, battery temperature, and conversion efficiency; the photovoltaic agent senses the current irradiation, module temperature, and inverter efficiency; and the electric vehicle agent senses the vehicle battery status and the user's travel plan.

[0180] In one embodiment, based on the carbon evaluation parameters of each key dimension of the park energy system, the comprehensive carbon emission rating of the park energy system is determined, including: using a preset triangular membership function to calculate the index value of the carbon evaluation parameter of each key dimension to obtain the membership degree of each key dimension carbon evaluation parameter to each evaluation level; for each evaluation level, the target weight of each key dimension carbon evaluation parameter and the membership degree of each key dimension carbon evaluation parameter to the evaluation level are weighted and summed to determine the comprehensive membership degree of the comprehensive carbon emission rating of the park energy system to the evaluation level; based on the comprehensive membership degree of the comprehensive carbon emission rating of the park energy system to each evaluation level, the evaluation level with the highest comprehensive membership degree is used as the comprehensive carbon emission rating of the park energy system.

[0181] For example, based on national, industry, and local standard limit requirements for park energy management, carbon emission management, and flexibility management related indicators, the recommended values ​​or limit value requirements for the current standards and specifications for rating this indicator as "high, average, or poor" are determined. Based on the recommended values ​​and limit values ​​of the dimensional carbon evaluation parameters determined by the relevant standards and specifications, the function parameters of the triangular membership model are determined, which include:

[0182]

[0183] Among them, μ(x) is the triangular membership function; x is the index value of the carbon evaluation parameter of each key dimension; α is the recommended value indicating a high indicator rating; b is the recommended value indicating a general indicator rating; and c is the recommended value indicating a poor indicator rating.

[0184] For example, the triangular membership function is used to calculate the membership degree of each key dimension carbon evaluation parameter to each evaluation level. Subsequently, for each evaluation level, the target weight of each key dimension carbon evaluation parameter is multiplied by its membership degree to that level, and the sum is calculated to obtain the comprehensive membership degree of the comprehensive carbon emissions rating to that evaluation level.

[0185] For example, suppose there are three key dimensional carbon evaluation parameters, namely A, B, and C, and the index values ​​of each key dimensional carbon evaluation parameter are known. By bringing the values ​​of each index into the triangular membership model, the membership degree of each evaluation level can be calculated (assuming that the membership degree of A belonging to high, general, and poor is recorded as A1, A2, and A3; the membership degree of B belonging to high, general, and poor is recorded as B1, B2, and B3; the membership degree of C belonging to high, general, and poor is recorded as C1, C2, and C3). For each evaluation level, the respective comprehensive membership is obtained by summing the product of the weight and the membership. That is, the comprehensive membership degree for the evaluation level "high" = A1×w a +B1×w b+C1×w c , where w α is the target weight corresponding to the key dimension carbon assessment parameter A; w b The target weight corresponding to the key dimension carbon assessment parameter B; w C The target weight corresponding to the key dimension carbon assessment parameter C. Similarly, the comprehensive carbon emissions rating is derived from the combined membership of the evaluation grades of "Fair" and "Poor." Finally, the evaluation grade with the highest comprehensive membership is used as the comprehensive carbon emissions rating of the park energy system.

[0186] According to the above implementation method, the level with the highest comprehensive membership directly corresponds to the "dominant level" of the park's carbon performance. The results are concise and clear, making it easy for managers to quickly identify and make improvements.

[0187] Figure 2 This is a structural block diagram of a park flexible resource operation device considering interactive carbon reduction evaluation according to an embodiment of the present invention.

[0188] like Figure 2 As shown, the park flexible resource operation device considering interactive carbon reduction evaluation may include:

[0189] A screening module 510 is configured to screen the carbon evaluation parameters of each dimension based on the index values ​​of the carbon evaluation parameters of each dimension of the park energy system to obtain a plurality of key carbon evaluation parameters;

[0190] A construction module 520 is configured to construct an objective function using the weight of each of the key dimensional carbon evaluation parameters as an independent variable, the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as a discrimination, and maximizing the discrimination as a goal;

[0191] A solution module 530 is configured to solve the objective function for a maximum value and obtain target weights of the carbon assessment parameters of each key dimension;

[0192] A determination module 540 is configured to determine a comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension;

[0193] The scheduling module 550 is used to perform carbon reduction scheduling on the park energy system when the comprehensive carbon emission evaluation value does not meet the preset requirements.

[0194] In one embodiment, Figure 3 As shown, the screening module 510 includes:

[0195] An indicator cumulative contribution rate determination unit 511 is configured to determine the indicator cumulative contribution rate of each of the dimensional carbon evaluation parameters based on the indicator value of each of the dimensional carbon evaluation parameters;

[0196] An adding unit 512 is configured to add the corresponding dimensional carbon evaluation parameter to the high contribution rate parameter set when the cumulative contribution rate of the indicator is greater than a preset cumulative contribution rate threshold;

[0197] The high-independence parameter set unit 513 is configured to perform independence calculations on the carbon evaluation parameters of each dimension in the high-contribution parameter set, and to screen parameters in the high-contribution parameter set based on the independence scores of the carbon evaluation parameters of each dimension to obtain a high-independence parameter set.

[0198] The sorting unit 514 is used to sort the independence scores of the carbon evaluation parameters of each dimension in the high independence parameter set in descending order, and take the first K dimensional carbon evaluation parameters as the key dimensional carbon evaluation parameters; wherein, the ratio of the sum of the variances of the index values ​​of the first K dimensional carbon evaluation parameters to the sum of the variances of the index values ​​of each dimensional carbon evaluation parameter in the high independence parameter set is greater than or equal to a first threshold, and K is less than or equal to a second threshold, and the first threshold is less than the second threshold.

[0199] In one embodiment, Figure 4 As shown, the building block 520 includes:

[0200] The contribution value unit 521 is used to multiply the weight of each key dimension carbon evaluation parameter by its respective index value to obtain the contribution value of each key dimension carbon evaluation parameter;

[0201] The contribution average unit 522 is used to calculate the average of the contribution values ​​of each of the key dimensional carbon assessment parameters to obtain a contribution average value;

[0202] A discrimination determination unit 523 is configured to determine the discrimination based on the sum of squares of differences between the contribution values ​​of the carbon assessment parameters of each key dimension and the contribution average value;

[0203] The objective function construction unit 524 is configured to construct the objective function using the weights of the carbon assessment parameters of the key dimensions as independent variables and maximizing the discrimination as a goal.

[0204] In one embodiment, Figure 5 As shown, the solution module 530 includes:

[0205] A population initialization unit 531 is used to initialize a population, wherein the population includes a plurality of individuals, each individual corresponds to a candidate weight vector, and the candidate weight vector includes the weights of the carbon assessment parameters of each key dimension;

[0206] A discrimination calculation unit 532 is configured to perform discrimination calculation on the candidate weight vector corresponding to each individual in the population of this iteration based on the objective function to obtain the discrimination of each individual in the population of this iteration;

[0207] Iterative unit 533 is configured to determine, if the highest discrimination degree among the discrimination degrees of the individuals in the population of this iteration does not meet a preset condition, a selection probability of each individual in the population of this iteration based on a ratio between the discrimination degrees of each individual in the population of this iteration and the sum of the discrimination degrees of each individual in the population of this iteration; screen individuals in the population of this iteration based on the selection probability of each individual in the population of this iteration to obtain a parent population; randomly select parent individuals from the parent population for pairing to obtain parent individual pairs; perform crossover calculation on candidate weight vectors corresponding to the parent individual pairs based on a random crossover coefficient to obtain multiple offspring individuals, and use the multiple offspring individuals as the population for the next iteration;

[0208] The target weight determination unit 534 is configured to stop iteration when the highest discrimination meets a preset condition, and determine the target weight of each of the key dimension carbon assessment parameters based on the candidate weight vector corresponding to the individual corresponding to the highest discrimination.

[0209] In one embodiment, Figure 6 As shown, the determining module 540 includes:

[0210] The carbon emission evaluation value unit 541 is used to multiply the index value of each key dimension carbon evaluation parameter by its respective target weight to obtain the carbon emission evaluation value of each key dimension carbon evaluation parameter;

[0211] The comprehensive carbon emission evaluation value unit 542 is used to sum up the various carbon emission evaluation values ​​to obtain a comprehensive carbon emission evaluation value of the park energy system.

[0212] In one embodiment, Figure 7 As shown, the scheduling module 550 includes:

[0213] A comprehensive carbon emission rating determination unit 551 is configured to determine a comprehensive carbon emission rating of the park energy system based on each of the key carbon evaluation parameters of the park energy system;

[0214] A reward function determination unit 552 is configured to determine a reward function for the agent based on the comprehensive carbon emission rating of the park energy system and the carbon evaluation parameters of each key dimension;

[0215] An action space construction unit 553 is configured to construct a state space of the agent based on the operating environment data of the park energy system, and to construct an action space of the agent based on the output power of each flexible resource of the park energy system at each time;

[0216] The interactive learning unit 554 is used to adopt the intelligent agent to sample action individuals from the action space and conduct interactive learning with the state space, and calculate the interactive learning results based on the reward function to obtain the reward value of each action individual, and output the action individual with the largest reward value as the carbon reduction scheduling plan of the park energy system, wherein the carbon reduction scheduling plan of the park energy system includes the target output power of each of the flexible resources within each of the times.

[0217] In one embodiment, Figure 8 As shown, the comprehensive carbon emission rating determination unit 551 includes:

[0218] The membership calculation subunit 5511 is used to calculate the index value of each key dimension carbon evaluation parameter using a preset triangular membership function to obtain the membership degree of each key dimension carbon evaluation parameter to each evaluation level;

[0219] The comprehensive membership determination subunit 5512 is configured to perform a weighted summation of the target weight of each key dimension carbon evaluation parameter and the degree of membership of each key dimension carbon evaluation parameter to the evaluation level for each evaluation level, to determine the comprehensive membership of the comprehensive carbon emission rating of the park energy system to the evaluation level;

[0220] The comprehensive carbon emission rating subunit 5513 is used to take the evaluation level with the highest comprehensive membership as the comprehensive carbon emission rating of the park energy system based on the comprehensive membership of the comprehensive carbon emission rating of the park energy system to each of the evaluation levels.

[0221] For the description of specific functions and examples of each module and submodule of the system in the embodiment of the present invention, please refer to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0222] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0223] The embodiment of the present invention further provides a park flexible resource operation system considering interactive carbon reduction evaluation, including:

[0224] at least one processor; and a memory communicatively coupled to the at least one processor;

[0225] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods in the embodiments of the present invention.

[0226] The beneficial effects of the park flexible resource operation system considering interactive carbon reduction evaluation in the embodiment of the present invention are equivalent to the beneficial effects of the above-mentioned park flexible resource operation method considering interactive carbon reduction evaluation, and will not be repeated here.

[0227] An embodiment of the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any one of the methods in the embodiments of the present invention.

[0228] The beneficial effects of the storage medium of the present invention are equivalent to the beneficial effects of the above-mentioned park flexible resource operation method considering interactive carbon reduction evaluation, and will not be described in detail here.

[0229] Figure 9 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present invention is shown. Electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 800 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0230] like Figure 9 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0231] Multiple components in the electronic device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0232] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the flexible resource operation method for a park considering interactive carbon reduction evaluation. For example, in some embodiments, the flexible resource operation method for a park considering interactive carbon reduction evaluation can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the flexible resource operation method for a park considering interactive carbon reduction evaluation described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured in any other appropriate manner (eg, by means of firmware) to execute a park flexible resource operation method that considers interactive carbon reduction evaluation.

[0233] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0234] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0235] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0236] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0237] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0238] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0239] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present invention can be achieved. This is not limited herein.

[0240] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A flexible resource operation method for a park considering interactive carbon reduction evaluation, characterized in that: include: Based on the index values ​​of the carbon evaluation parameters of each dimension of the park energy system, multiple key carbon evaluation parameters are screened from the carbon evaluation parameters of each dimension; The objective function is constructed by taking the weight of each of the key dimensional carbon evaluation parameters as an independent variable, taking the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as the discrimination, and taking maximizing the discrimination as the goal; Solving the objective function for the maximum value to obtain the target weight of each of the key dimension carbon assessment parameters; Determine the comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension; When the comprehensive carbon emission evaluation value does not meet the preset requirements, the park energy system is scheduled for carbon reduction.

2. The method according to claim 1, characterized in that The indicator values ​​of the carbon evaluation parameters of each dimension of the park energy system are screened from the carbon evaluation parameters of each dimension to obtain multiple key carbon evaluation parameters, including: Determine the cumulative contribution rate of the carbon evaluation parameters in each dimension based on the indicator value of each dimension carbon evaluation parameter; When the cumulative contribution rate of the indicator is greater than the preset cumulative contribution rate threshold, the corresponding dimensional carbon evaluation parameter is added to the high contribution rate parameter set; Performing independence calculations on each dimensional carbon evaluation parameter in the high contribution rate parameter set, and screening parameters in the high contribution rate parameter set based on the independence scores of the carbon evaluation parameters in each dimensional dimension to obtain a high independence parameter set; Sort the independence scores of the carbon evaluation parameters of each dimension in the high independence parameter set in descending order, and take the first K carbon evaluation parameters of each dimension as the key carbon evaluation parameters; Among them, the ratio of the sum of the variances of the index values ​​of the first K dimensional carbon evaluation parameters to the sum of the variances of the index values ​​of each of the dimensional carbon evaluation parameters in the high independence parameter set is greater than or equal to a first threshold, and K is less than or equal to a second threshold, and the first threshold is less than the second threshold.

3. The method according to claim 1, characterized in that The objective function is constructed by taking the weight of each of the key dimensional carbon evaluation parameters as an independent variable, taking the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as the discrimination, and taking maximizing the discrimination as the goal, including: Multiply the weight of each key dimension carbon evaluation parameter by its respective indicator value to obtain the contribution value of each key dimension carbon evaluation parameter; Calculate the average of the contribution values ​​of the carbon assessment parameters of each key dimension to obtain the average contribution value; Determining the discrimination based on the sum of squares of differences between the contribution values ​​of the carbon assessment parameters of each key dimension and the contribution average; The objective function is constructed by taking the weights of the carbon evaluation parameters of each key dimension as independent variables and maximizing the discrimination as the goal.

4. The method according to claim 1, wherein Solving the objective function for the maximum value to obtain the target weights of the carbon assessment parameters of each key dimension includes: Initializing a population, wherein the population includes a plurality of individuals, each individual corresponds to a candidate weight vector, and the candidate weight vector includes the weights of the carbon assessment parameters of each key dimension; Based on the objective function, calculating the discrimination of the candidate weight vector corresponding to each individual in the population of this iteration to obtain the discrimination of each individual in the population of this iteration; If the highest discrimination degree among the discrimination degrees of the individuals in the population of this iteration does not meet a preset condition, determining the selection probability of each individual in the population of this iteration based on the ratio between the discrimination degree of each individual in the population of this iteration and the sum of the discrimination degrees of each individual in the population of this iteration; screening individuals in the population of this iteration based on the selection probability of each individual in the population of this iteration to obtain a parent population; randomly selecting parent individuals from the parent population for pairing to obtain parent individual pairs; performing crossover calculation on candidate weight vectors corresponding to the parent individual pairs based on a random crossover coefficient to obtain multiple offspring individuals, and using the multiple offspring individuals as the population for the next iteration; The iteration is stopped when the highest discrimination degree meets the preset conditions, and the target weights of the carbon assessment parameters of each key dimension are determined based on the candidate weight vectors corresponding to the individuals corresponding to the highest discrimination degree.

5. The method according to claim 1, wherein Determining the comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension includes: Multiplying the index value of each of the key dimensional carbon evaluation parameters by their respective target weights to obtain the carbon emission evaluation value of each of the key dimensional carbon evaluation parameters; The carbon emission evaluation values ​​are summed to obtain a comprehensive carbon emission evaluation value of the park energy system.

6. The method according to claim 1, characterized in that The carbon reduction scheduling of the park energy system includes: Determining a comprehensive carbon emission rating of the park energy system based on the carbon evaluation parameters of each key dimension of the park energy system; Determining a reward function for the agent based on the comprehensive carbon emission rating of the park energy system and the carbon evaluation parameters of each key dimension; Constructing the state space of the agent based on the operating environment data of the park energy system, and constructing the action space of the agent based on the output power of each flexible resource of the park energy system at each time; The intelligent agent is used to sample action individuals from the action space and interact with the state space for learning, and the reward value of each action individual is calculated based on the reward function to obtain the reward value of each action individual, and the action individual with the largest reward value is output as the carbon reduction scheduling plan of the park energy system, wherein the carbon reduction scheduling plan of the park energy system includes the target output power of each flexible resource within each time.

7. The method according to claim 6, characterized in that Determining the comprehensive carbon emission rating of the park energy system based on the carbon evaluation parameters of each key dimension of the park energy system includes: Using a preset triangular membership function, the index value of each key dimension carbon evaluation parameter is calculated to obtain the membership degree of each key dimension carbon evaluation parameter to each evaluation level; For each evaluation level, the target weight of each key dimension carbon evaluation parameter and the degree of membership of each key dimension carbon evaluation parameter to the evaluation level are weighted and summed to determine the comprehensive degree of membership of the comprehensive carbon emission rating of the park energy system to the evaluation level; Based on the comprehensive membership of the comprehensive carbon emission rating of the park energy system to each of the evaluation levels, the evaluation level with the highest comprehensive membership is used as the comprehensive carbon emission rating of the park energy system.

8. A flexible resource operation device for a park considering interactive carbon reduction evaluation, characterized in that: include: A screening module is used to screen the carbon evaluation parameters of each dimension based on the indicator values ​​of the carbon evaluation parameters of each dimension of the park energy system to obtain multiple key carbon evaluation parameters; A construction module is used to construct an objective function using the weight of each of the key dimensional carbon evaluation parameters as an independent variable, the product of the index value of each of the key dimensional carbon evaluation parameters and the weight as the discrimination, and maximizing the discrimination as the goal; A solution module, configured to solve the objective function for a maximum value and obtain target weights of the carbon assessment parameters of each key dimension; A determination module, configured to determine a comprehensive carbon emission evaluation value of the park energy system based on the indicator values ​​and target weights of the carbon evaluation parameters of each key dimension; The scheduling module is used to perform carbon reduction scheduling on the park energy system when the comprehensive carbon emission evaluation value does not meet the preset requirements.

9. A flexible resource operation system for a park considering interactive carbon reduction evaluation, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images