Total energy consumption prediction method, system and device and storable medium

Abstract

The invention discloses a total energy consumption prediction method, system and equipment and a storable medium, and the method comprises the steps: S1, energy consumption intensity measurement and calculation: the energy consumption intensity of a target region is measured and calculated, and the energy consumption of raw materials and renewable energy sources are not brought into the energy consumption intensity; s2, energy consumption intensity reduction rate measurement and calculation: the energy consumption intensity reduction rate is measured and calculated by using the target year energy consumption intensity and the reference year energy consumption intensity; and S3, predicting the total energy consumption of the target year region: predicting the total energy consumption of the target year region under the condition of meeting the constraint that the energy consumption intensity of the target year is reduced compared with the energy consumption intensity of the reference year. The design not only predicts the total energy consumption of the target year region, but also does not bring the raw material energy consumption and the renewable energy into the factor influence of the energy consumption intensity on the total energy consumption prediction, so that the algorithm model is more in line with the actual production and living state.

Description

Technical Field

[0001] The invention relates to a total energy consumption prediction method, belongs to the field of energy consumption prediction and analysis, and is specifically suitable for eliminating the influence of raw material energy and renewable energy on the total energy consumption calculation. Background Art

[0002] Total energy consumption (also known as: total energy consumption) refers to the sum of various energy sources consumed by various industries of the national economy and households in a certain region in a certain period of time. Energy consumption intensity refers to the energy consumed by a region for each unit of regional GDP produced in a certain period of time. In recent years, in order to meet the reasonable energy demand for high-quality development and accelerate the transformation of energy consumption dual control to carbon emission dual control, the energy consumption intensity calculation method has been adjusted, and raw material energy and renewable energy are not included in the energy consumption intensity, which will have a certain impact on regional energy development. Therefore, a total energy consumption prediction method considering the impact of double deductions on energy consumption intensity is proposed, and the reasonable total energy consumption scale that meets the energy consumption intensity constraint of the target year is analyzed after the energy consumption intensity calculation method is adjusted to ensure that the reasonable energy demand for high-quality development of the region is guaranteed.

[0003] A large part of my country's coal consumption is used as chemical or other raw materials, which is different from the situation in developed countries where oil or natural gas is used as chemical raw materials. General calculations lead to some good projects being restricted by energy consumption indicators, which in turn affects the development of advanced and high-end products and the optimization of industrial structure.

[0004] At present, in the field of regional energy consumption forecasting, commonly used methods include: time series method, regression model method, etc. This type of method mainly focuses on the mathematical relationship between the time series of total energy consumption and the time series of economic factors, and believes that there is a one-to-one correspondence between energy demand and the development of economic factors. It uses statistical principles to establish a mathematical model to forecast total energy consumption. None of the above methods analyze the impact of energy intensity on total energy consumption forecasting after the energy intensity measurement method is adjusted, that is, raw material energy and renewable energy are not included in energy intensity. Summary of the invention

[0005] The purpose of the present invention is to overcome the problems of general calculation and unreasonable modeling in the prior art, and to provide a method, system, device and storable medium for predicting total energy consumption that does not include raw material energy and renewable energy in the impact of energy consumption intensity on the total energy consumption prediction.

[0006] To achieve the above objectives, the technical solution of the present invention is:

[0007] A total energy consumption prediction method, comprising:

[0008] S1. Energy intensity calculation: Calculate the energy intensity of the target area. Energy consumption of raw materials and renewable energy are not included in the energy intensity.

[0009] S2. Calculation of energy intensity reduction rate: Calculate the energy intensity reduction rate using the target year energy intensity and the base year energy intensity;

[0010] S3. Forecast of total regional energy consumption in the target year: Based on the region's measured baseline data and target data, and while satisfying the constraint of the reduction rate of energy consumption intensity in the target year compared to the base year, forecast the total regional energy consumption in the target year.

[0011] In step S1, energy consumption intensity is not included in raw material energy and renewable energy. Tot for:

[0012]

[0013] Where: N Tot is the total regional energy consumption, unit: 10,000 tons of standard coal; N Rm is the energy consumption of regional raw materials, unit: 10,000 tons of standard coal; N Res is the regional renewable energy consumption, N Res It is the value converted into standard coal energy, unit: 10,000 tons of standard coal; G Tot It is the regional GDP, unit: trillion yuan.

[0014] In step S2, the target annual energy consumption intensity E Tot,i Energy intensity E compared to the base year Tot,0 EDR i for:

[0015]

[0016] Divide both the numerator and denominator of the above formula by N Tot,0 , and factorize it to get EDR i The formula is transformed into:

[0017]

[0018] Where: N Rm,i / N Tot,i The proportion of raw material energy consumption in the total energy consumption in the target year, that is, PT Rm,i ; N Res,i / N Tot,i is the proportion of renewable energy in total energy consumption in the target year, i.e. PT Res,i ; N Res,0 / N Tot,0 is the proportion of raw material energy consumption in the total energy consumption in the base year, that is, PT Rm,0 ; N Res,0 / N Tot,0 is the proportion of renewable energy in total energy consumption in the base year, i.e. PT Res,0 ; G Tot,0 / G Tot,i The growth rate of the gross regional product in the target year compared with the base year, i.e. GSD Tot,i ; N Tot,i / N Tot,0 The total energy consumption in the target year is developing faster than that in the base year, i.e. NSD Tot,i ; EDR i0 EDR is the rate of decrease in energy intensity in the target year compared to the base year when the impact of raw material energy consumption and renewable energy is not considered. i0 =1-NSD Tot,i / GSD Tot,i .

[0019] In step S3, first, the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i It is predicted that the energy intensity in the target year will decrease by EDR compared with the base year. i Under the constraint of Tot,i for:

[0020]

[0021] Including: Base year GDP G Tot,0 、Total energy consumption N Tot,0 , Raw material energy consumption ratio PT Rm,0 , Renewable energy share PT Res,0 All are known values.

[0022] In step S3, G Tot,i , PT Rm,i , PT Res,i The prediction method is: refer to the GDP and carbon neutrality target data in the five-year planning documents of relevant regions, calculate the benchmark data based on the historical data of regional energy economic development, and construct a multivariate linear regression model based on time series, respectively, for the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make predictions.

[0023] In step S3, the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The forecast is made based on the energy consumption and renewable energy proportion data of historical years; the specific method is as follows:

[0024] S3.1 Historical annual raw material energy consumption ratio PT Rm , Renewable energy share PT Res The univariate regression analysis was performed separately, and the regression equation was i represents the target year, and according to the goodness of fit R 2 Scope of the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make combined forecasts;

[0025] Where: R 2 for:

[0026]

[0027]

[0028] Among them, X is the observed index value, and the observed index is the historical annual raw material energy consumption ratio PT Rm or the proportion of renewable energy in historical years PT Res , is the regression fitting value, is the average value of the observed index value in the historical time series T, n is the serial number of the historical time series T, k is the kth year in the historical time series, and T is the historical time series; m1 and m2 are the slope and intercept of the straight line fitted by the univariate regression method;

[0029] S3.1.1 When R 2 When the value range of is between [d1,1], that is, the observed index value is strongly correlated with the historical data, [d1,1] is the set strong correlation judgment set, then the target year data is predicted according to the historical annual change trend:

[0030] a. If the observed indicator value X shows an increasing trend (i.e. m1>0), the observed indicator value for the target year is calculated as follows:

[0031] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0032]

[0033] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0034] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0035]

[0036] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0037] b. If the observed index value X is on a downward trend (i.e. m1<0), the observed index value for the target year is calculated as follows:

[0038] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0039]

[0040] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0041] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0042]

[0043] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0044] S3.1.2 When R 2 When the value range of is between [0, d1], that is, the observed index value is not strongly correlated with the historical data, [0, d1] is the set weak correlation judgment set, then the target year data is predicted based on the multi-year average of historical years:

[0045] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0046]

[0047] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0048] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0049]

[0050] Among them, PT Res,k is the proportion of renewable energy in the Kth year in history; generally speaking, d1 is taken as 0.7.

[0051] S3.2 The target year GDP will be predicted Tot,i , Raw material energy consumption ratio PTRm,i , Renewable energy share PT Res,i The predicted value is brought into the formula:

[0052]

[0053] The energy intensity in the target year decreases by EDR compared to the base year. i Under the constraints of Tot,i .

[0054] The method further includes S4, calculating the impact of raw material energy consumption and renewable energy on the energy intensity reduction rate without including energy intensity;

[0055] In step S4, in order to calculate the impact of raw material energy consumption and renewable energy deduction on the regional energy intensity reduction rate, the energy intensity reduction rate EDR can be calculated. i The formula can be further simplified as:

[0056] EDR i =EDR i0 +EDR_N Rm,i +EDR_N Res,i ;

[0057] Among them: The impact of raw material energy consumption on the regional energy intensity reduction rate EDR_N Rm,i for:

[0058]

[0059] The impact of renewable energy on the regional energy intensity reduction rate EDR_N Res,i for:

[0060]

[0061] A total energy consumption prediction system, specifically comprising:

[0062] Energy consumption intensity calculation module: used to calculate the energy consumption intensity of the target area;

[0063] The energy consumption intensity calculation module is used to implement the following method: S1, energy consumption intensity calculation: calculate the energy consumption intensity of the target area, and raw material energy and renewable energy are not included in the energy consumption intensity;

[0064] Energy consumption intensity is not included in raw material energy and renewable energy. Tot for:

[0065]

[0066] Where: N Tot is the total regional energy consumption, unit: 10,000 tons of standard coal; N Rmis the energy consumption of regional raw materials, unit: 10,000 tons of standard coal; N Res is the regional renewable energy consumption, N Res It is the value converted into standard coal energy, unit: 10,000 tons of standard coal; G Tot It is the regional GDP, unit: trillion yuan.

[0067] Energy consumption intensity reduction rate calculation module: used to calculate the energy consumption intensity reduction rate;

[0068] The energy consumption intensity reduction rate calculation module is used to implement the following method: S2, energy consumption intensity reduction rate calculation: using the target year energy consumption intensity and the base year energy consumption intensity to calculate the energy consumption intensity reduction rate;

[0069] Target annual energy intensity E Tot,i Energy intensity E compared to the base year Tot,0 EDR i for:

[0070]

[0071] Divide both the numerator and denominator of the above formula by N Tot,0 , and factorize it to get EDR i The formula is transformed into:

[0072]

[0073] Where: N Rm,i / N Tot,i The proportion of raw material energy consumption in the total energy consumption in the target year, that is, PT Rm,i ; N Res,i / N Tot,i is the proportion of renewable energy in total energy consumption in the target year, i.e. PT Res,i ; N Res,0 / N Tot,0 is the proportion of raw material energy consumption in the total energy consumption in the base year, that is, PT Rm,0 ; N Res,0 / N Tot,0 is the proportion of renewable energy in total energy consumption in the base year, i.e. PT Res,0 ; G Tot,0 / G Tot,i The growth rate of the gross regional product in the target year compared with the base year, i.e. GSD Tot,i ; N Tot,i / N Tot,0 The total energy consumption in the target year is developing faster than that in the base year, i.e. NSD Tot,i ; EDR i0 EDR is the rate of decrease in energy intensity in the target year compared to the base year when the impact of raw material energy consumption and renewable energy is not considered. i0 =1-NSD Tot,i / GSDTot,i .

[0074] Target year regional total energy consumption forecasting module: used to forecast the target year regional total energy consumption.

[0075] The target year regional total energy consumption prediction module is used to implement the following method: S3, target year regional total energy consumption prediction: based on the region's measured baseline data and target data, the target year regional total energy consumption is predicted while satisfying the constraint of the target year energy consumption intensity reduction rate compared to the base year energy consumption intensity.

[0076] First, the target year GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i It is predicted that the energy intensity in the target year will decrease by EDR compared with the base year. i Under the constraint of Tot,i for:

[0077]

[0078] Including: Base year GDP G Tot,0 、Total energy consumption N Tot,0 , Raw material energy consumption ratio PT Rm,0 , Renewable energy share PT Res,0 All are known values.

[0079] In step S3, the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The forecast is made based on the energy consumption and renewable energy proportion data of historical years; the specific method is as follows:

[0080] S3.1 Historical annual raw material energy consumption ratio PT Rm , Renewable energy share PT Res The univariate regression analysis was performed separately, and the regression equation was i represents the target year, and according to the goodness of fit R 2 Scope of the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make combined forecasts;

[0081] Where: R 2 for:

[0082]

[0083]

[0084] Among them, X is the observed index value, and the observed index is the historical annual raw material energy consumption ratio PT Rm or the proportion of renewable energy in historical years PT Res , is the regression fitting value, is the average value of the observed index value in the historical time series T, n is the serial number of the historical time series T, k is the kth year in the historical time series, and T is the historical time series; m1 and m2 are the slope and intercept of the straight line fitted by the univariate regression method;

[0085] S3.1.1 When R 2 When the value range of is between [d1,1], that is, the observed index value is strongly correlated with the historical data, [d1,1] is the set strong correlation judgment set, then the target year data is predicted according to the historical annual change trend:

[0086] a. If the observed indicator value X shows an increasing trend (i.e. m1>0), the observed indicator value for the target year is calculated as follows:

[0087] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0088]

[0089] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0090] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0091]

[0092] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0093] b. If the observed index value X is on a downward trend (i.e. m1<0), the observed index value for the target year is calculated as follows:

[0094] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0095]

[0096] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0097] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0098]

[0099] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0100] S3.1.2 When R 2 When the value range of is between [0, d1], that is, the observed index value is not strongly correlated with the historical data, [0, d1] is the set weak correlation judgment set, then the target year data is predicted based on the multi-year average of historical years:

[0101] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0102]

[0103] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0104] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0105]

[0106] Among them, PT Res,k is the proportion of renewable energy in the Kth year in history; generally speaking, d1 is taken as 0.7.

[0107] S3.2 The target year GDP will be predicted Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The predicted value is brought into the formula:

[0108]

[0109] The energy intensity in the target year decreases by EDR compared to the base year. i Under the constraints of Tot,i .

[0110] The system also includes an energy intensity reduction rate impact module: used to evaluate the impact of double deductions on the regional energy intensity reduction rate.

[0111] The energy consumption intensity reduction rate influence module is used to implement the following method: S4, calculating the influence of raw material energy consumption and renewable energy on the energy consumption intensity reduction rate without including energy consumption intensity;

[0112] In order to calculate the impact of raw material energy consumption and renewable energy deduction on the regional energy intensity reduction rate, the energy intensity reduction rate EDR can be calculated. i The formula can be further simplified as:

[0113] EDR i =EDR i0 +EDR_N Rm,i +EDR_N Res,i ;

[0114] Among them: (1) The impact of raw material energy consumption on the regional energy intensity reduction rate EDR_N Rm,i for:

[0115]

[0116] (2) The impact of renewable energy on the regional energy intensity reduction rate EDR_N Res,i for:

[0117]

[0118] A computing device for predicting total energy consumption includes a memory and a processor, wherein the memory is used to store computer program codes and transmit the computer program codes to the processor; and the processor is used to execute a method for predicting total energy consumption according to instructions in the computer program codes.

[0119] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for predicting total energy consumption is implemented.

[0120] Compared with the prior art, the present invention has the following beneficial effects:

[0121] 1. In a total energy consumption prediction method of the present invention, energy consumption intensity is first calculated, then the energy consumption intensity reduction rate is calculated, and finally the total energy consumption in the target year is predicted. The modeling of this method is more reasonable, and the raw material energy and renewable energy are not included in the factors affecting the total energy consumption prediction by energy consumption intensity, so that the algorithm model is more in line with the actual production and living conditions, and the reliability of the calculation results is higher, which can better reflect the energy consumption status of the current region.

[0122] 2. A total energy consumption prediction system of the present invention includes: an energy consumption intensity calculation module, an energy consumption intensity reduction rate calculation module and a target year regional total energy consumption prediction module, and the system is used to implement the steps of the total energy consumption prediction method provided in any of the above technical solutions. Therefore, the decoding system also includes all the beneficial effects of the total energy consumption prediction method provided in any of the above technical solutions, which will not be repeated here.

[0123] 3. A total energy consumption prediction device of the present invention includes a processor and a memory, the memory is used to store computer program code and transmit the computer program code to the processor, and the processor is used to execute the total energy consumption prediction method provided in any of the above technical solutions according to the instructions in the computer program code. Therefore, the device also includes all the beneficial effects of the total energy consumption prediction method provided in any of the above technical solutions, which will not be repeated here.

[0124] 4. The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for predicting the total amount of energy consumption provided in any of the above technical solutions. Therefore, the computer-readable storage medium also includes all the beneficial effects of the method for predicting the total amount of energy consumption provided in any of the above technical solutions, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0125] Figure 1 It is a logic flow chart of the present invention.

[0126] Figure 2 is a block diagram of a computing system of the present invention.

[0127] Figure 3 is a block diagram of a computing device of the present invention. DETAILED DESCRIPTION

[0128] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0129] The principle of the present invention is described as follows:

[0130] The present invention relates to a total energy consumption forecasting method considering the influence of "double deduction" of energy consumption intensity, and belongs to the field of energy consumption forecasting and analysis. The purpose of this design is to address the current total energy consumption forecasting that fails to consider the adjustment of energy consumption intensity calculation method, that is, raw material energy and renewable energy are not included in the influence of energy consumption intensity on the total energy consumption forecasting. Therefore, based on the latest energy consumption intensity calculation method, an energy consumption intensity reduction rate calculation model considering the influence of "double deduction" is constructed. Under the condition of meeting the constraint of the energy consumption intensity reduction rate of the target year compared with the base year energy consumption intensity, combined with regional economic growth, raw material energy and renewable energy proportion changes, the total energy consumption of the target year region is predicted, and the influence of raw material energy and renewable energy not included in the energy consumption intensity on the energy consumption intensity reduction rate is analyzed and calculated. This method overcomes the problem that the previous forecasting methods pay more attention to the mathematical correlation between the time series of total energy consumption and the time series of economic factors, but do not consider the problem of energy consumption intensity calculation method adjustment on total energy consumption. The method proposed in this design has clear logical thinking, reliable and objective data sources, strong operability, and can calculate the reasonable total energy consumption scale of the target year to ensure that the reasonable energy demand for high-quality development of the region is guaranteed.

[0131] Example 1: See Figure 1 , a total energy consumption prediction method, comprising:

[0132] S1. Energy intensity calculation: Calculate the energy intensity of the target area. Energy consumption of raw materials and renewable energy are not included in the energy intensity.

[0133] S2. Calculation of energy intensity reduction rate: Calculate the energy intensity reduction rate using the target year energy intensity and the base year energy intensity;

[0134] S3. Forecast of total regional energy consumption in the target year: Based on the region's measured baseline data and target data, and while satisfying the constraint of the reduction rate of energy consumption intensity in the target year compared to the base year, forecast the total regional energy consumption in the target year.

[0135] In step S1, energy consumption intensity is not included in raw material energy and renewable energy. Tot for:

[0136]

[0137] Where: N Tot is the total regional energy consumption, unit: 10,000 tons of standard coal; N Rm is the energy consumption of regional raw materials, unit: 10,000 tons of standard coal; N Res is the regional renewable energy consumption, N Res It is the value converted into standard coal energy, unit: 10,000 tons of standard coal; G Tot It is the regional GDP, unit: trillion yuan.

[0138] In step S2, the target annual energy consumption intensity E Tot,i Energy intensity E compared to the base year Tot,0 EDR i for:

[0139]

[0140] Divide both the numerator and denominator of the above formula by N Tot,0 , and factorize it to get EDR i The formula is transformed into:

[0141]

[0142] Where: N Rm,i / N Tot,i The proportion of raw material energy consumption in the total energy consumption in the target year, that is, PT Rm,i ; N Res,i / N Tot,i is the proportion of renewable energy in total energy consumption in the target year, i.e. PT Res,i ; N Res,0 / N Tot,0 is the proportion of raw material energy consumption in the total energy consumption in the base year, that is, PT Rm,0 ; N Res,0 / N Tot,0 is the proportion of renewable energy in total energy consumption in the base year, i.e. PT Res,0 ; G Tot,0 / G Tot,i The growth rate of the gross regional product in the target year compared with the base year, i.e. GSD Tot,i ; N Tot,i / N Tot,0 The total energy consumption in the target year is developing faster than that in the base year, i.e. NSD Tot,i ; EDR i0 EDR is the rate of decrease in energy intensity in the target year compared to the base year when the impact of raw material energy consumption and renewable energy is not considered. i0 =1-NSD Tot,i / GSD Tot,i .

[0143] In step S3, first, the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i It is predicted that the energy intensity in the target year will decrease by EDR compared with the base year. i Under the constraint of Tot,i for:

[0144]

[0145] Including: Base year GDP G Tot,0 、Total energy consumption N Tot,0 , Raw material energy consumption ratio PT Rm,0 , Renewable energy share PT Res,0 All are known values.

[0146] In step S3, G Tot,i , PT Rm,i , PT Res,i The prediction method is: refer to the GDP and carbon neutrality target data in the five-year planning documents of relevant regions, calculate the benchmark data based on the historical data of regional energy economic development, and construct a multivariate linear regression model based on time series, respectively, for the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make predictions.

[0147] The method further includes S4, calculating the impact of raw material energy consumption and renewable energy on the energy intensity reduction rate without including energy intensity;

[0148] In step S4, in order to calculate the impact of raw material energy consumption and renewable energy deduction on the regional energy intensity reduction rate, the energy intensity reduction rate EDR can be calculated. i The formula can be further simplified as:

[0149] EDR i =EDR i0 +EDR_N Rm,i +EDR_N Res,i ;

[0150] Among them: (1) The impact of raw material energy consumption on the regional energy intensity reduction rate EDR_N Rm,i for:

[0151]

[0152] (2) The impact of renewable energy on the regional energy intensity reduction rate EDR_N Res,i for:

[0153]

[0154] According to the above EDR i From the formula, we can know:

[0155] 1. When the raw material energy consumption and renewable energy proportion of energy consumption in the target year remain the same as those in the base year, or the sum of raw material energy consumption and renewable energy proportion of energy consumption in the target year remains the same as those in the base year, that is, when PT Rm,i =PT Rm,0 , PT Res,i =PTRes,0 When or when PT Rm,i +PT Res,i =PT Rm,0 +PT Res,0 When the energy intensity reduction rate is , the energy intensity reduction rate is consistent with that without considering the impact of “double deduction”, that is, EDR i =EDR i0 The energy intensity reduction rate is only determined by the regional energy consumption development speed NSD. Tot,i , Regional GDP growth rate GSD Tot,i 2. When the sum of raw material energy consumption and renewable energy ratio in the target year is greater than the sum of raw material energy consumption and renewable energy ratio in the base year, that is, PT Rm,i +PT Res,i >PT Rm,0 +PT Res,0 When the energy intensity calculation method is adjusted, the energy intensity reduction scale will be increased, that is, EDR i >EDR i0 , indicating that the "double deduction" has played a positive role in reducing regional energy intensity. 3. When the sum of raw material energy consumption and renewable energy in the target year is less than the sum of raw material energy consumption and renewable energy in the base year, that is, PT Rm,i +PT Res,i <PT Rm,0 +PT Res,0 When the energy intensity calculation method is adjusted, the energy intensity reduction rate, i.e. EDR, will be reduced. i <EDR i0 , indicating that the “double deduction” has a reverse negative effect on the reduction of regional energy consumption intensity.

[0156] Embodiment 2:

[0157] Embodiment 2 is substantially the same as Embodiment 1, except that:

[0158] In step S3, the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The forecast is made based on the energy consumption and renewable energy proportion data of historical years; the specific method is as follows:

[0159] S3.1 Historical annual raw material energy consumption ratio PT Rm , Renewable energy share PT Res The univariate regression analysis was performed separately, and the regression equation was i represents the target year, and according to the goodness of fit R 2 Scope of the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make combined forecasts;

[0160] Where: R 2for:

[0161]

[0162]

[0163] Among them, X is the observed index value, and the observed index is the historical annual raw material energy consumption ratio PT Rm or the proportion of renewable energy in historical years PT Res , is the regression fitting value, is the average value of the observed index value in the historical time series T, n is the serial number of the historical time series T, k is the kth year in the historical time series, and T is the historical time series; m1 and m2 are the slope and intercept of the straight line fitted by the univariate regression method;

[0164] S3.1.1 When R 2 When the value range of is between [d1,1], that is, the observed index value is strongly correlated with the historical data, [d1,1] is the set strong correlation judgment set, then the target year data is predicted according to the historical annual change trend:

[0165] a. If the observed indicator value X shows an increasing trend (i.e. m1>0), the observed indicator value for the target year is calculated as follows:

[0166] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0167]

[0168] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0169] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0170]

[0171] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0172] b. If the observed index value X is on a downward trend (i.e. m1<0), the observed index value for the target year is calculated as follows:

[0173] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PTRm,i for:

[0174]

[0175] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0176] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0177]

[0178] Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year;

[0179] S3.1.2 When R 2 When the value range of is between [0, d1], that is, the observed index value is not strongly correlated with the historical data, [0, d1] is the set weak correlation judgment set, then the target year data is predicted based on the multi-year average of historical years:

[0180] When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for:

[0181]

[0182] Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year;

[0183] When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for:

[0184]

[0185] Among them, PT Res,k is the proportion of renewable energy in the Kth year in history; generally speaking, d1 is taken as 0.7.

[0186] S3.2 The target year GDP will be predicted Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The predicted value is brought into the formula:

[0187]

[0188] The energy intensity in the target year decreases by EDR compared to the base year.i Under the constraints of Tot,i .

[0189] Embodiment 3:

[0190] See also Figure 1 In order to better illustrate the technical principle of the present invention, the implementation steps of the present invention are further described below in combination with specific examples. Taking the energy consumption level calculation of a certain region from 2021 to 2025 as an example, the specific calculation method is as follows:

[0191] Due to the adjustment of the measurement method, raw material energy and renewable energy are not included in the energy intensity. According to the five-year development plan of the region, the energy intensity of the i-th year (target year) is reduced by the rate constraint value EDR compared with the base year. i The total value of regional production increase in the base year is G Tot,0 4.3 trillion yuan, and the total energy consumption is N Tot,0 16,000 tons of standard coal, renewable energy and raw material energy consumption as a percentage of total energy consumption PT Rm,0 PT Res,0 17.5% and 4.3% respectively. ; Estimated GDP in the target year (calculated at comparable prices in the base year) G Tot,i 5.9 trillion yuan (average annual growth rate of 6.5%, GSD Tot,i 137%), the proportion of renewable energy and raw material energy in total energy consumption PT Rm,i PT Res,i They increased by 19.0% and 6.5% respectively.

[0192] According to the formula in step S3, the target annual energy consumption N Tot,i It is 19,800 tons of standard coal, and the total energy consumption growth rate is NSD Tot,i It is 124%, with an average annual growth rate of 4.3%.

[0193] According to the formula in step S4, the impact of not including raw material energy and renewable energy in energy intensity control on the energy intensity reduction rate is calculated. In the target year, raw material energy and renewable energy account for 2.2 and 1.5 percentage points of energy consumption respectively compared with the base year, that is: PT Rm,i +PT Res,i >PT Rm,0 +PT Res,0 Among them: the impact of raw material energy consumption on the regional energy intensity reduction rate EDR_N Rm,i The impact of renewable energy on the regional energy intensity reduction rate EDR_N Res,i If raw material energy and renewable energy are included in the energy intensity, the energy intensity in the target year will decrease by EDR compared with the energy intensity in the base year. i0It is 9.73%. It can be seen that the increase in the proportion of raw material energy and renewable energy in energy consumption in the target year compared with the base year has a positive effect on the reduction rate of energy intensity.

[0194] In summary, taking the planning data of a certain region from 2021 to 2025 as an example, according to the constructed energy intensity calculation model considering the impact of "double deductions", combined with the target constraint value of the target year energy intensity reduction rate compared with the base year and the forecast of regional economic growth, raw material energy consumption, and the proportion of renewable energy, the total regional energy consumption scale was calculated, and the impact of excluding raw material energy consumption and renewable energy from energy intensity control on the energy intensity reduction rate was analyzed, proving the feasibility of this method.

[0195] Embodiment 4:

[0196] See also Figure 2 , a total energy consumption prediction system, specifically comprising:

[0197] Energy consumption intensity calculation module: used to calculate the energy consumption intensity of the target area; the energy consumption intensity calculation module is used to implement step S1 as described in Example 1.

[0198] Energy consumption intensity reduction rate calculation module: used to calculate the energy consumption intensity reduction rate; the energy consumption intensity reduction rate calculation module is used to implement step S2 as described in Example 1.

[0199] The target year regional energy consumption total amount prediction module is used to predict the target year regional energy consumption total amount. The target year regional energy consumption total amount prediction module is used to implement step S3 as described in Example 1.

[0200] The system further comprises an energy consumption intensity reduction rate impact module: used to evaluate the impact of double deductions on the regional energy consumption intensity reduction rate. The energy consumption intensity reduction rate impact module is used to implement step S4 as described in Example 1.

[0201] Embodiment 5:

[0202] See also Figure 3 A computing device for predicting total energy consumption includes a memory and a processor, wherein the memory is used to store computer program code and transmit the computer program code to the processor; the processor is used to execute a method for predicting total energy consumption according to instructions in the computer program code.

[0203] Embodiment 6:

[0204] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for predicting total energy consumption is implemented.

[0205] Generally speaking, the computer instructions for implementing the method of the present invention may be carried in any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media, except for the signal itself that is temporarily propagating.

[0206] Computer-readable storage media, for example, may be, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with a system, device or device for executing instructions.

[0207] One or more programming languages ​​or their combinations can be used to write computer program codes for performing the operation of the present invention. These programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and also include conventional procedural programming languages, such as C language or similar programming languages. In particular, Python language suitable for neural network calculations and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through various types of networks, including a local area network (LAN) or a wide area network (WAN), or an Internet connection is performed through an Internet service provider.

[0208] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for predicting total energy consumption, characterized in that: The total energy consumption prediction method comprises the following steps: S1. Energy intensity calculation: Calculate the energy intensity of the target area. Energy consumption of raw materials and renewable energy are not included in the energy intensity. S2. Calculation of energy intensity reduction rate: Calculate the energy intensity reduction rate using the target year energy intensity and the base year energy intensity; S3. Forecast of total regional energy consumption in the target year: Based on the region's measured baseline data and target data, and while satisfying the constraint of the reduction rate of energy consumption intensity in the target year compared to the base year, forecast the total regional energy consumption in the target year.

2. A method for predicting total energy consumption according to claim 1, characterized in that: In step S1, energy consumption intensity is not included in raw material energy and renewable energy. Tot for: Where: N Tot is the total regional energy consumption, unit: 10,000 tons of standard coal; N Rm is the energy consumption of regional raw materials, unit: 10,000 tons of standard coal; N Res is the regional renewable energy consumption, N Res It is the value converted into standard coal energy, unit: 10,000 tons of standard coal; G Tot It is the regional GDP, unit: trillion yuan.

3. A method for predicting total energy consumption according to claim 2, characterized in that: In step S2, the target annual energy consumption intensity E Tot,i Energy intensity E compared to the base year Tot,0 EDR i for: Divide both the numerator and denominator of the above formula by N Tot,0 , and factorize it to get EDR i The formula is transformed into: Where: N Rm,i / N Tot,i The proportion of raw material energy consumption in the total energy consumption in the target year, that is, PT Rm,i ; N Res,i / N Tot,i is the proportion of renewable energy in total energy consumption in the target year, i.e. PT Res,i ; N Res,0 / N Tot,0 is the proportion of raw material energy consumption in the total energy consumption in the base year, that is, PT Rm,0 ; N Res,0 / N Tot,0 is the proportion of renewable energy in total energy consumption in the base year, i.e. PT Res，0 ; G Tot,0 / G Tot,i The growth rate of the gross regional product in the target year compared with the base year, i.e. GSD Tot，i ; N Tot,i / N Tot,0 The total energy consumption in the target year is developing faster than that in the base year, i.e. NSD Tot，i ; EDR i0 EDR is the rate of decrease in energy intensity in the target year compared to the base year when the impact of raw material energy consumption and renewable energy is not considered. i0 =1-NSD Tot,i / GSD Tot,i .

4. A method for predicting total energy consumption according to claim 3, characterized in that: In step S3, first, the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i It is predicted that the energy intensity in the target year will decrease by EDR compared with the base year. i Under the constraint of Tot,i for: Including: Base year GDP G Tot,0 、Total energy consumption N Tot,0 , Raw material energy consumption ratio PT Rm,0 , Renewable energy share PT Res,0 All are known values.

5. A method for predicting total energy consumption according to claim 4, characterized in that: In step S3, G Tot,i , PT Rm,i , PT Res,i The prediction method is: refer to the GDP and carbon neutrality target data in the five-year planning documents of relevant regions, calculate the benchmark data based on the historical data of regional energy economic development, and construct a multivariate linear regression model based on time series, respectively, for the target year regional GDP G Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make predictions.

6. A method for predicting total energy consumption according to claim 5, characterized in that: In step S3, the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The forecast is made based on the energy consumption and renewable energy proportion data of historical years; the specific method is as follows: S3.1 Historical annual raw material energy consumption ratio PT Rm , Renewable energy share PT Res The univariate regression analysis was performed separately, and the regression equation was i represents the target year, and according to the goodness of fit R 2 Scope of the target year raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i Make combined forecasts; Where: R 2 for: Among them, X is the observed index value, and the observed index is the historical annual raw material energy consumption ratio PT Rm or the proportion of renewable energy in historical years PT Res , is the regression fitting value, is the average value of the observed index value in the historical time series T, n is the serial number of the historical time series T, k is the kth year in the historical time series, and T is the historical time series; m1 and m2 are the slope and intercept of the straight line fitted by the univariate regression method; S3.1.1 When R 2 When the value range of is between [d1,1], that is, the observed index value is strongly correlated with the historical data, [d1,1] is the set strong correlation judgment set, then the target year data is predicted according to the historical annual change trend: a. If the observed indicator value X shows an increasing trend (i.e. m1>0), the observed indicator value for the target year is calculated as follows: Rm , then the target year raw material energy consumption ratio PT Rm,i for: Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year; When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for: Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year; b. If the observed index value X is on a downward trend (i.e. m1<0), the observed index value for the target year is calculated as follows: When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for: Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year; When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for: Among them, PT Res,k is the proportion of renewable energy in the Kth year in the historical year; S3.1.2 When R 2 When the value range of is between [0, d1], that is, the observed index value is not strongly correlated with the historical data, [0, d1] is the set weak correlation judgment set, then the target year data is predicted based on the multi-year average of historical years: When the observed indicator is the historical annual raw material energy consumption ratio PT Rm , then the target year raw material energy consumption ratio PT Rm,i for: Among them, PT Rm,k is the proportion of raw material energy consumption in the Kth year in the historical year; When the observed indicator is the proportion of renewable energy in historical years PT Res , then the proportion of renewable energy in the target year is PT Res,i for: Among them, PT Res,k is the proportion of renewable energy in the Kth year in history; generally speaking, d1 is taken as 0.

7. S3.2 The target year GDP will be predicted Tot,i , Raw material energy consumption ratio PT Rm,i , Renewable energy share PT Res,i The predicted value is brought into the formula: The energy intensity in the target year decreases by EDR compared to the base year. i Under the constraints of Tot,i .

7. A total energy consumption prediction system, characterized in that: The system is used to execute the total energy consumption prediction method according to any one of claims 1 to 6, specifically comprising: Energy consumption intensity calculation module: used to calculate the energy consumption intensity of the target area; Energy consumption intensity reduction rate calculation module: used to calculate the energy consumption intensity reduction rate; Target year regional total energy consumption forecasting module: used to forecast the target year regional total energy consumption.

8. A computing device for predicting total energy consumption, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method according to any one of claims 1 to 6 according to the instructions in the computer program code.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 6 is implemented.

Images