CN115829113A - Carbon emission estimation method based on energy consumption data - Google Patents
Carbon emission estimation method based on energy consumption data Download PDFInfo
- Publication number
- CN115829113A CN115829113A CN202211490858.1A CN202211490858A CN115829113A CN 115829113 A CN115829113 A CN 115829113A CN 202211490858 A CN202211490858 A CN 202211490858A CN 115829113 A CN115829113 A CN 115829113A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- carbon emission
- consumption data
- data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 79
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 79
- 238000005265 energy consumption Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000003066 decision tree Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 230000001419 dependent effect Effects 0.000 claims abstract description 4
- 230000005611 electricity Effects 0.000 claims description 15
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 10
- -1 heat Substances 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 239000003345 natural gas Substances 0.000 claims description 5
- 239000003245 coal Substances 0.000 claims description 4
- 239000000295 fuel oil Substances 0.000 claims description 4
- 239000003502 gasoline Substances 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000002283 diesel fuel Substances 0.000 claims 1
- 230000001105 regulatory effect Effects 0.000 description 26
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 235000006732 Torreya nucifera Nutrition 0.000 description 1
- 244000111306 Torreya nucifera Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
技术领域technical field
本发明涉及碳排放测算及预测技术领域，尤其是指一种基于能源消费数据的碳排放估算方法。The invention relates to the technical field of carbon emission measurement and prediction, in particular to a method for estimating carbon emission based on energy consumption data.
背景技术Background technique
目前针对碳排放量的预测有以GDP、工业增加值和能源活动对碳排放的影响来对碳排放进行分析和预测，例如常用的经典模型有Kaya恒等式、MERGE模型和IPAC模型等；也有通过数据分析方法构建模型对碳排放量进行预测的，常见的模型有多元神经网络、DDEPM模型和GM(1，1)模型等，这些模型或方法均可为碳排放量的测算与预测提供有效的理论分析与可行验证。由于碳排放量难以直接计量，通常采用碳排放系数乘以各种能源消耗量来计算碳排放，但由于全国各地客观存在的能源结构差异和变化，导致碳排放系数的地域适应性和更新及时性无法得到保障，导致采用单一的碳排放预测模型地区适应性较差，预测的烟排放结果不够可靠和准确。At present, the prediction of carbon emissions includes the analysis and prediction of carbon emissions based on GDP, industrial added value and the impact of energy activities on carbon emissions. For example, the commonly used classic models include Kaya identity, MERGE model and IPAC model; there are also data Analytical methods Build models to predict carbon emissions. Common models include multivariate neural networks, DDEPM models, and GM (1,1) models. These models or methods can provide effective theories for the calculation and prediction of carbon emissions Analysis and feasibility verification. Since carbon emissions are difficult to measure directly, carbon emission coefficients are usually multiplied by various energy consumption to calculate carbon emissions. However, due to the objective differences and changes in energy structures across the country, the regional adaptability and update timeliness of carbon emission coefficients Unable to be guaranteed, resulting in the poor adaptability of regions using a single carbon emission prediction model, and the predicted smoke emission results are not reliable and accurate enough.
发明内容Contents of the invention
本发明的目的是克服现有技术中不同地区的碳排放量通过单一模型测算导致的结果不够可靠和准确的弊端，提出了一种基于能源消费数据的碳排放估算方法，可以根据地区的企业和行业的能源消费特点、地域能源结构特色和发展变化，选择最佳的模型进行对应的碳排放估算，估算的结果准确可靠。The purpose of the present invention is to overcome the disadvantages of unreliable and accurate results caused by the measurement and calculation of carbon emissions in different regions by a single model in the prior art, and propose a method for estimating carbon emissions based on energy consumption data, which can be based on regional enterprises and The industry's energy consumption characteristics, regional energy structure characteristics and development changes, select the best model to estimate the corresponding carbon emissions, and the estimated results are accurate and reliable.
本发明的目的是通过下述技术方案予以实现的：提出了基于能源消费数据的碳排放估算方法，包括如下步骤：The purpose of the present invention is achieved through the following technical solutions: a method for estimating carbon emissions based on energy consumption data is proposed, including the following steps:
S1、获取历史规上行业能源消费数据，并对其进行清洗得到能源数据清单；S1. Obtain historical energy consumption data of industries above the designated size, and clean it to obtain a list of energy data;
S2、根据数据清单中的用能数据得到规上行业的历史碳排放量；S2. According to the energy consumption data in the data list, obtain the historical carbon emissions of the regulated industries;
S3、根据规上行业的历史碳排放量得到规上行业的历史碳排放电力系数；S3. Obtain the historical carbon emission power coefficient of the regulated industry according to the historical carbon emissions of the regulated industry;
S4、将规上行业的历史碳排放电力系数作为因变量，选择自变量构建ARIMAX时间序列模型和XGBoost梯度提升决策树模型，输出测试集拟合结果并计算两种模型的各区域平均偏差和中位数偏差；S4. Take the historical carbon emission power coefficient of the regulated industry as the dependent variable, select the independent variable to construct the ARIMAX time series model and the XGBoost gradient boosting decision tree model, output the fitting results of the test set, and calculate the average deviation and median of the two models in each region digit deviation;
S5、选择输出偏差最小的模型作为最佳预测模型；S5. Selecting the model with the smallest output deviation as the best prediction model;
S6、利用最佳预测模型得到实时的规上行业碳排放量测算数据。S6. Use the best forecasting model to obtain real-time carbon emission measurement data of the designated industries.
作为优选，S1包括如下步骤：Preferably, S1 includes the following steps:
提取规上行业的能源消费数据，剔除能源消费数据清单中的异常数据得到清洗后的规上能源Extract the energy consumption data of the regulated industries, eliminate the abnormal data in the energy consumption data list and get the regulated energy after cleaning
1数据清单。1 data list.
作为优选，所述用能数据包括有能源种类和能源数量；所述能源种类包括有电力、原煤、热力、汽油、柴油、燃料油和天然气。Preferably, the energy consumption data includes energy types and energy quantities; the energy types include electricity, raw coal, heat, gasoline, diesel, fuel oil and natural gas.
作为优选，S2包括如下步骤：As preferably, S2 comprises the following steps:
根据用能数据中的能源类型对应的标准碳排放折算系数与能源的消耗量进行单位统一后相乘，得到每种能源的理论碳排放量；According to the standard carbon emission conversion coefficient corresponding to the energy type in the energy consumption data and the energy consumption, the unit is unified and multiplied to obtain the theoretical carbon emission of each energy;
依次获取每种能源的理论碳排放量并进行相加汇总，得到规上行业的历史碳排放量。The theoretical carbon emissions of each energy source are obtained in turn and summed up to obtain the historical carbon emissions of the regulated industries.
作为优选，S3包括如下步骤：As preferably, S3 comprises the following steps:
根据规上行业的历史碳排放量与对应周期内规上行业用电量的比值作为规上行业的历史碳排放电力系数。According to the ratio of the historical carbon emissions of the regulated industries to the electricity consumption of the regulated industries in the corresponding period, it is used as the historical carbon emission power coefficient of the regulated industries.
作为优选，S4中，分别计算两个模型的输出值偏差，其中输出值偏差计算公式为：As a preference, in S4, the output value deviations of the two models are calculated respectively, wherein the output value deviation calculation formula is:
其中，yi为真实值，
作为优选，S4还包括：将年份及用电量作为自变量，构建ARIMAX时间序列模型，获取以年份为单位获取数据集，划分测试集和训练集，遍历p和q两项参数的设置取值范围，自动搜索使模型BIC最小的参数组合。Preferably, S4 also includes: using the year and electricity consumption as independent variables, constructing an ARIMAX time series model, obtaining a data set in units of years, dividing a test set and a training set, and traversing the setting values of the two parameters p and q range, to automatically search for the parameter combination that minimizes the BIC of the model.
作为优选，S4还包括：将行业、年份以及用电量作为自变量，构建XGBoost梯度提升决策树算法模型；以年份为单位获取数据集；采用留出法基于8:2的比例将数据集划分训练集和测试集，遍历弱学习器个数和树的深度在设置范围内的数值组合，选择平均偏差最小的组合作为模型参数。As a preference, S4 also includes: using the industry, year and electricity consumption as independent variables, constructing the XGBoost gradient boosting decision tree algorithm model; obtaining the data set in units of years; using the hold-out method to divide the data set based on the ratio of 8:2 The training set and the test set, traverse the numerical combinations of the number of weak learners and the depth of the tree within the set range, and select the combination with the smallest average deviation as the model parameter.
作为优选，S6包括：利用最佳预测模型的预测得到的规上行业碳排放电力系数与规上行业实时电量数据进行相乘，得到规上行业实时的碳排放量测算数据。Preferably, S6 includes: multiplying the carbon emission power coefficient of the regulated industry obtained from the prediction of the best prediction model by the real-time electricity data of the regulated industry to obtain the real-time carbon emission measurement data of the regulated industry.
本发明具备的有益效果为：提出了一种基于能源消费数据的碳排放估算方法，分别构建用于碳排放测算的ARIMAX时间序列模型和XGBoost梯度提升决策树模型，可以根据地区的企业和行业的能源消费特点、地域能源结构特色和发展变化，选择最佳的模型进行对应的碳排放估算，估算的结果准确可靠。The beneficial effects of the present invention are as follows: a carbon emission estimation method based on energy consumption data is proposed, and an ARIMAX time series model and an XGBoost gradient boosting decision tree model for carbon emission measurement and calculation are respectively constructed, which can be used according to the needs of enterprises and industries in the region According to the characteristics of energy consumption, regional energy structure characteristics and development changes, the best model is selected to estimate the corresponding carbon emissions, and the estimated results are accurate and reliable.
具体实施方式Detailed ways
下面结合实施例对本发明进一步描述。The present invention is further described below in conjunction with embodiment.
实施例：Example:
基于能源消费数据的碳排放估算方法，包括如下步骤：The method for estimating carbon emissions based on energy consumption data includes the following steps:
S1、获取历史规上行业能源消费数据，并对其进行清洗得到规上行业能源数据清单。S1. Obtain the historical energy consumption data of industries on the scale, and clean it to obtain the energy data list of the industries on the scale.
其中，S1包括如下步骤：Wherein, S1 includes the following steps:
提取规上行业的能源消费数据，剔除能源消费数据清单中的异常数据得到清洗后的规上能源数据清单。Extract the energy consumption data of the regulated industries, and eliminate the abnormal data in the energy consumption data list to obtain the regulated energy data list after cleaning.
具体的，规上行业能源消费数据可来源于统计局发布的某省各地市历年《统计年鉴》中所记录的30多个工业行业规模以上企业的综合能耗和多种能源汇总用能数据，用能数据包括电力、原煤、热力、汽油、柴油、燃料油和天然气等。Specifically, the energy consumption data of industries above the designated size can be derived from the comprehensive energy consumption and the aggregate energy consumption data of various energy sources recorded in the "Statistical Yearbooks" of more than 30 industrial enterprises above the designated size in the past years issued by the Statistics Bureau. Energy consumption data include electricity, raw coal, heat, gasoline, diesel, fuel oil, and natural gas.
S2、根据数据清单中的用能数据得到规上行业的历史碳排放量。S2. According to the energy consumption data in the data inventory, obtain the historical carbon emissions of the regulated industries.
S2包括如下步骤：S2 includes the following steps:
根据用能数据中的能源类型对应的标准碳排放折算系数与能源的消耗量进行单位统一后相乘，得到每种能源的理论碳排放量；According to the standard carbon emission conversion coefficient corresponding to the energy type in the energy consumption data and the energy consumption, the unit is unified and multiplied to obtain the theoretical carbon emission of each energy;
依次获取每种能源的理论碳排放量并进行相加汇总，得到规上行业的历史碳排放量。The theoretical carbon emissions of each energy source are obtained in turn and summed up to obtain the historical carbon emissions of the regulated industries.
所述用能数据包括有能源种类和能源数量；所述能源种类包括有电力、原煤、热力、汽油、柴油、燃料油和天然气。The energy consumption data includes energy types and energy quantities; the energy types include electricity, raw coal, heat, gasoline, diesel, fuel oil and natural gas.
S3、根据规上行业的历史碳排放量得到规上行业的历史碳排放电力系数。S3. According to the historical carbon emissions of the regulated industries, the historical carbon emission power coefficients of the regulated industries are obtained.
具体的，根据规上行业的历史碳排放量与对应周期内规上行业用电量的比值作为规上行业的历史碳排放电力系数。Specifically, the ratio of the historical carbon emissions of the regulated industries to the electricity consumption of the regulated industries in the corresponding period is used as the historical carbon emission power coefficient of the regulated industries.
S4、将规上行业的历年碳排放电力系数作为因变量，选择自变量构建ARIMAX时间序列模型和XGBoost梯度提升决策树模型，输出测试集拟合结果并计算两种模型的各区域平均偏差和中位数偏差。S4. Taking the electricity coefficient of carbon emissions of the regulated industry over the years as the dependent variable, select the independent variable to construct the ARIMAX time series model and the XGBoost gradient boosting decision tree model, output the fitting results of the test set and calculate the average deviation and median of the two models in each region digit deviation.
S4中，分别计算两个模型的输出值偏差，其中输出值偏差计算公式为：In S4, the output value deviation of the two models is calculated respectively, and the calculation formula of the output value deviation is:
其中，yi为真实值，
进一步的，S4还包括：将年份及用电量作为自变量，构建ARIMAX时间序列模型，获取以年份为单位获取数据集，划分测试集和训练集，遍历p和q两项参数的设置取值范围，自动搜索使模型BIC最小的参数组合。Further, S4 also includes: using the year and electricity consumption as independent variables, building an ARIMAX time series model, obtaining a data set in units of years, dividing the test set and training set, and traversing the setting values of the two parameters p and q range, to automatically search for the parameter combination that minimizes the BIC of the model.
进一步的，S4还包括：将行业、年份以及用电量作为自变量，构建XGBoost梯度提升决策树算法模型；以年份为单位获取数据集；采用留出法基于8:2的比例将数据集划分训练集和测试集，遍历弱学习器个数和树的深度在设置范围内的数值组合，选择平均偏差最小的组合作为模型参数。Further, S4 also includes: using the industry, year, and electricity consumption as independent variables to construct an XGBoost gradient boosting decision tree algorithm model; obtaining data sets in units of years; using the hold-out method to divide the data sets based on the ratio of 8:2 The training set and the test set, traverse the numerical combinations of the number of weak learners and the depth of the tree within the set range, and select the combination with the smallest average deviation as the model parameter.
S5、选择输出偏差最小的模型作为最佳预测模型。S5. Select the model with the smallest output deviation as the best prediction model.
S6、利用最佳预测模型得到实时的规上行业碳排放量测算数据。S6. Use the best forecasting model to obtain real-time carbon emission measurement data of the designated industries.
具体的，利用最佳预测模型的预测得到的规上行业碳排放电力系数与规上行业实时电量数据进行相乘，得到规上行业实时的碳排放量测算数据。Specifically, the carbon emission power coefficient of the regulated industry obtained from the prediction of the best prediction model is multiplied by the real-time electricity data of the regulated industry to obtain the real-time carbon emission measurement data of the regulated industry.
获取历史行业整体的能源消费数据，并对其进行清洗得到行业整体能源数据清单，作为本实施例的一种可替换方案，可以根据本申请说明书段落号0015-0027同样的方法，利用最佳预测模型预测得到行业整体的碳排放实时测算数据。Obtain the historical overall energy consumption data of the industry, and clean it to obtain the overall energy data list of the industry. As an alternative solution of this embodiment, the best forecast can be used according to the same method as paragraph number 0015-0027 of this application specification The model forecast obtains the real-time calculation data of carbon emissions of the industry as a whole.
作为本实施例的一种可替换方案，根据本申请说明书段落号0015-0027同样的方法，利用最佳预测模型预测得到行业整体的综合能耗实时测算数据。As an alternative solution of this embodiment, according to the same method as paragraph number 0015-0027 of the specification of this application, the best prediction model is used to predict and obtain the real-time measurement data of the comprehensive energy consumption of the industry as a whole.
具体的，获取某碳交易试点工业园区内200多家企业的用能数据和行业类型，用能种类主要包括电力、热力和天然气等，对其进行清洗得到企业能源数据清单，根据本申请说明书段落号0015-0027同样的方法，利用最佳预测模型预测得到试点园区企业的碳排放实时测算数据。Specifically, obtain the energy consumption data and industry types of more than 200 enterprises in a carbon trading pilot industrial park. The types of energy consumption mainly include electricity, heat and natural gas, etc., and clean them to obtain a list of enterprise energy data. According to the paragraphs of this application specification In the same way as No. 0015-0027, the best prediction model is used to predict and obtain the real-time carbon emission measurement data of enterprises in the pilot park.
作为本实施例的一种可替换方案，根据本申请说明书段落号0015-0027同样的方法，利用最佳预测模型预测得到试点园区企业的综合能耗实时测算数据。As an alternative solution of this embodiment, according to the same method as paragraph number 0015-0027 of this application specification, the real-time measurement data of the comprehensive energy consumption of enterprises in the pilot parks can be obtained by using the best prediction model.
以上所述的实施例只是本发明的一种较佳的方案，并非对本发明作任何形式上的限制，在不超出权利要求所记载的技术方案的前提下还有其它的变体及改型。The embodiment described above is only a preferred solution of the present invention, and does not limit the present invention in any form. There are other variations and modifications on the premise of not exceeding the technical solution described in the claims.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490858.1A CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490858.1A CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115829113A true CN115829113A (en) | 2023-03-21 |
Family
ID=85531540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211490858.1A Withdrawn CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829113A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | A Carbon Emission Assessment Method Based on Power Consumption Regression |
-
2022
- 2022-11-25 CN CN202211490858.1A patent/CN115829113A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | A Carbon Emission Assessment Method Based on Power Consumption Regression |
| CN116167669B (en) * | 2023-04-26 | 2023-07-21 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Predicting river dissolved oxygen time series based on stand-alone models and hybrid wavelet-based models | |
| CN110942247A (en) | Evaluation method for analyzing influence factors of power carbon emission and carbon emission efficiency | |
| CN105701559A (en) | Short-term load prediction method based on time sequence | |
| CN105205570A (en) | Power grid power sale quantity prediction method based on season time sequence analysis | |
| CN102073785A (en) | Daily gas load combination prediction method based on generalized dynamic fuzzy neural network | |
| CN106503851A (en) | A kind of improved Short-Term Load Forecasting Method based on wavelet analysises | |
| CN107248013A (en) | A kind of monthly electricity demand forecasting method for considering diversified economy factor | |
| CN108647987A (en) | House valuation of assets method | |
| CN112446534A (en) | Construction period prediction method and device for power transmission and transformation project | |
| Dai et al. | The application of ARIMA model in forecasting population data | |
| CN116739368A (en) | Industrial park carbon emission level monitoring and evaluating method based on energy big data | |
| CN116993030A (en) | Reservoir pressure salty taste adjustment method and system under variable conditions | |
| CN112990500A (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
| CN114548552A (en) | Carbon emission prediction method and device, and electronic device | |
| CN102930155A (en) | Method and device for acquiring early-warming parameters of power demands | |
| CN117592598A (en) | A monthly power decomposition and forecasting method based on the Prophet-X-12-ARIMA combination model | |
| CN115829113A (en) | Carbon emission estimation method based on energy consumption data | |
| CN113837912A (en) | Method for analyzing influence factors of carbon emission in construction industry | |
| CN118071164A (en) | A method for estimating carbon emission reduction potential based on the prediction of carbon emission change per key indicator | |
| CN110458392A (en) | A kind of wind power plant O&M performance appraisal management method and system | |
| CN110909492B (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN114254916A (en) | Multi-dimensional supplier risk real-time early warning method with power grid service characteristics | |
| CN117371610A (en) | Carbon emission monitoring method and system | |
| CN106296464A (en) | Big data multiple spot load forecasting method | |
| CN108665090B (en) | Prediction method of saturated load of urban power grid based on principal component analysis and Verhulst model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230321 |