Multi-industry and multi-time scale terminal energy demand prediction method and device

Abstract

The invention discloses a multi-industry and multi-time scale terminal energy demand prediction method and device, and relates to the technical field of energy prediction and planning. The method comprises the following steps: firstly, acquiring terminal energy consumption data of each industry of a predicted region in historical years and energy demand influence factors of the predicted years, and inputting the data into a pre-constructed energy demand prediction model; the industry annual total demand is obtained through prediction based on the terminal energy consumption data of each industry and the energy demand influence factor through the industry annual prediction sub-model, and the industry annual total demand is decomposed based on the energy substitution coefficient through the energy type decomposition sub-model to obtain the energy type demand of each industry. And decomposing the energy type demand quantity based on the seasonal fluctuation factor through the monthly decomposition sub-model to obtain the monthly demand quantity of each energy type. According to the invention, on the basis of different industry influence factors and different influence degrees, regional, industry and month-by-month energy exhibition is realized, the prediction accuracy is high, and a favorable basis can be provided for decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of energy forecasting and planning, and in particular to a method and device for forecasting terminal energy demand in multiple industries and at multiple time scales. Background Art

[0002] In the context of low-carbon transformation, accurate prediction of future energy demand is of great significance for energy conservation, emission reduction and future energy planning. At present, energy demand forecasting mostly focuses on predicting the nonlinear relationship between various influencing factors and future energy demand and carbon emissions, and attempts to improve the accuracy of the overall forecast trend by learning more relevant features. However, it ignores the differences in influencing factors and influencing mechanisms in different fields, different energy types and different time scales. The forecast results lack practical reference value, and a single total demand forecast cannot fully reflect the demand distribution in the region, and the value it can provide for subsequent analysis is limited.

[0003] Therefore, at this stage, there is an urgent need for a terminal energy demand forecasting solution that distinguishes different industries, different energy types, and different time scales to solve the above problems. Summary of the invention

[0004] The present invention provides a method and device for predicting terminal energy demand in multiple industries and multiple time scales, so as to solve the problem that the existing prediction technology lacks distinction between different industries, energy types and time scales, resulting in insufficient prediction accuracy and single results, and lack of practical reference value.

[0005] The present invention is achieved through the following technical solutions:

[0006] A first aspect of the present invention provides a method for predicting terminal energy demand in multiple industries and at multiple time scales, comprising:

[0007] Acquire the terminal energy consumption data of the forecast area in the historical years and the energy demand influencing factors of the forecast area in the forecast year, wherein the terminal energy consumption data and the energy demand influencing factors are distinguished from different industries;

[0008] Input the terminal energy consumption data and energy demand influencing factors of each industry into a pre-constructed energy demand forecasting model to obtain the total annual demand, energy type demand and monthly demand of the industry in the forecast area in the forecast year; wherein the energy demand forecasting model is constructed from bottom to top using a factor decomposition method, with the upper layer being an industry annual forecast sub-model, the middle layer being an energy type decomposition sub-model, and the lower layer being a monthly decomposition sub-model;

[0009] The industry annual forecast sub-model predicts the total annual demand of the industry based on the terminal energy consumption data and energy demand influencing factors of each industry. The energy type decomposition sub-model decomposes the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry. The monthly decomposition sub-model decomposes the energy type demand based on the seasonal fluctuation factor to obtain the monthly demand of each energy type.

[0010] The present invention realizes energy demand forecasting by region and industry based on the energy demand influencing factors in different forecast regions and industries, and obtains accurate forecasting results for each forecast industry by considering the different influencing factors and the degree of influence in different industries. In addition, the demand for each energy type is decomposed based on the total demand of the industry, and the monthly demand is decomposed based on the seasonal fluctuation factors of each industry, forming an accurate and comprehensive forecasting result, which makes up for the shortcomings of the existing technology and provides an effective reference for future energy decision-making.

[0011] Furthermore, the energy demand influencing factors include GDP growth rate, energy intensity and energy substitution coefficient, and the energy substitution coefficient is predicted based on the energy transformation policy.

[0012] Furthermore, the energy type decomposition sub-model is expressed as:

[0013]

[0014] Among them, DE pr,e,r,t represents the total annual demand for energy e by industry r in the forecast region pr in the forecast year t, DE pr,e,r,t-1 represents the total annual demand for energy e by industry r in year t-1, GDPR pr,r,t It represents the GDP growth rate of industry r in the forecast region pr in the forecast year t, IDR pr,r,t represents the energy intensity reduction rate of industry r in forecast region pr in forecast year t, SB pr,ee,e,t SB represents the amount of energy ee substituted by another energy e in the forecast region pr and industry t in the forecast year. pr,e,ee,t It represents the amount of substitution of one energy source e for another energy source ee in the forecast region pr and the forecast year t industry r.

[0015] Furthermore, the energy types include: electricity, coal, natural gas, oil and bioenergy.

[0016] Furthermore, the industries include: heating department, power generation department, hydrogen production department, life department and production department.

[0017] Furthermore, the monthly decomposition sub-model is expressed as:

[0018]

[0019] Among them, DE ELE,r,t,m represents the energy demand of industry r in forecast region pr in the mth month of forecast year t, DE pr,ELE,r,t represents the demand for energy e by the production sector in the forecast region pr in the forecast year t, DE Ho,ELE,r,t represents the energy demand of the living sector in the forecast region pr in the forecast year t, MF Ho,ELE,r,m represents the seasonal fluctuation factor of the electricity demand of the living sector in the mth month affected by the season, ∑ m MF Ho,ELE,r,m =1,DE Hp,ELE,r,t,m represents the energy demand of the hydrogen production sector in the forecast region pr in the mth month of the forecast year t.

[0020] A second aspect of the present invention provides a terminal energy demand forecasting device for multiple industries and multiple time scales, comprising:

[0021] A data acquisition module, used to acquire the terminal energy consumption data of the forecast area in the historical year, and the energy demand influencing factors of the forecast area in the forecast year, wherein the terminal energy consumption data and the energy demand influencing factors are distinguished from different industries;

[0022] Energy demand forecasting model, including industry annual forecasting sub-model, energy type decomposition sub-model and monthly decomposition sub-model;

[0023] The annual forecast sub-model is used to predict the total annual demand of each industry based on the terminal energy consumption data and energy demand influencing factors of each industry;

[0024] The energy type decomposition sub-model is used to decompose the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry;

[0025] The monthly decomposition sub-model is used to decompose the demand for the energy types based on seasonal fluctuation factors to obtain the monthly demand for each energy type.

[0026] The third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the terminal energy demand forecasting method for multiple industries and multiple time scales as described in any one of the first aspect of the present invention is implemented.

[0027] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the terminal energy demand forecasting method for multiple industries and multiple time scales as described in any one of the first aspects of the present invention.

[0028] The fifth aspect of the present invention provides a computer program product, characterized in that when the computer program product is run on a computer, the computer implements the multi-industry and multi-time scale terminal energy demand forecasting method as described in any one of the first aspects of the present invention.

[0029] Compared with the prior art, the present invention has the following advantages and beneficial effects: The energy demand forecasting scheme of the present invention starts from economic growth and energy intensity, and decomposes the demand of each year, province, industry, and energy type in the test area into monthly demand, which better reflects the impact of policy transformation on the terminal energy consumption structure of a province or industry, including the penetration rate of emission reduction technology deployment, such as the promotion of electric vehicles, the progress of coal to electricity and coal to gas, etc., providing data guidance for decision makers to achieve carbon peak and carbon neutrality goals, planning and policy formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0031] Figure 1 is a flow chart of a method for predicting terminal energy demand in multiple industries and multiple time scales according to an embodiment of the present invention;

[0032] Figure 2 is the terminal energy consumption (by energy type) of Province S under the baseline scenario predicted by the present invention;

[0033] Figure 3 The terminal energy consumption (by energy type) in Sichuan Province under the accelerated development scenario predicted by the present invention;

[0034] Figure 4 It is a schematic diagram of a terminal energy demand prediction device for multiple industries and multiple time scales according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0036] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to or inherent to other steps or units of the device.

[0037] The terms used in the various embodiments of the application are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the application. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meanings commonly understood by ordinary technicians in the field of the various embodiments of the application. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the application.

[0038] The embodiments of the present invention provide a method and device for predicting terminal energy demand in multiple industries and time scales, realizing a method for predicting energy demand by region, industry and month based on economic growth rate, energy intensity and transformation policy outlook, which is conducive to providing accurate and comprehensive forecasting data and providing valuable reference for future energy planning.

[0039] The industry outlook is crucial for the following three reasons: first, there are significant differences in economic growth rates and energy consumption reductions among industries, so they need to be differentiated to improve accuracy; second, there are significant differences in the month-to-month fluctuations in energy demand among industries, and the living sector is the main source of seasonal fluctuations in energy demand. Therefore, the seasonal fluctuations in overall energy demand in the future can be predicted by characterizing the fluctuation characteristics of demand in each industry and superimposing them; third, there are significant differences in the low-carbon transformation measures that can be taken by various industries, and there are significant differences in the choice of energy types and energy conversion efficiency in the transformation policies.

[0040] However, the current energy demand forecasting method lacks consideration of economic growth rate, energy intensity and transformation policy, resulting in inappropriate results and discussions that have no reference value. Therefore, the present invention proposes a multi-industry and multi-time scale terminal energy demand forecasting method based on economic growth rate, energy intensity and transformation policy outlook to solve this problem.

[0041] like Figure 1 Shown is a flow chart of a method for predicting terminal energy demand for multiple industries and multiple time scales according to an embodiment of the present invention, which includes the following steps.

[0042] 1. Establish energy demand forecasting model in advance.

[0043] The present invention adopts the factor decomposition method to construct a forecasting model from the bottom up. First, the total energy demand of a region or an industry is decomposed into two factors: economic total and energy intensity. According to the outlook for economic growth and energy intensity of each province and industry in the future, the total annual demand for terminal energy in each province and industry is obtained. Secondly, the annual demand for each energy variety is decomposed on the basis of the total annual energy demand. The outlook for the terminal energy consumption structure of a province or an industry is mainly affected by the transformation policy, including the penetration rate of emission reduction technology deployment, such as the promotion of electric vehicles, the promotion of coal to electricity, and the promotion of coal to gas. The model assumes that in the absence of policy intervention, the energy consumption structure of each industry will remain unchanged in the next year, and the simulation of the low-carbon transformation policy will be reflected in the change of the terminal energy consumption structure, thereby calculating the terminal demand of each energy variety in each region and industry. Finally, the annual demand of each variety is further decomposed into the demand of each month. The model uses seasonal fluctuation factors and industry superposition to decompose, that is, taking into account the differences in seasonal energy consumption characteristics of different industries, setting their monthly fluctuations based on historical data, and then superimposing the fluctuations in energy demand in different industries to obtain the monthly demand for each region, industry, and energy type. The upper layer is the industry annual forecast sub-model, the middle layer is the energy type decomposition sub-model, and the lower layer is the monthly decomposition sub-model. The bottom-up approach is a simple way to generate consistent forecasts. First, the forecast for each sequence is generated at the bottom level, and then these forecasts are added together to obtain the forecast for all sequences in the structure.

[0044] The data required for the forecast include historical annual terminal energy consumption data by industry in the forecast region (province), energy demand influencing factors that affect energy consumption, such as economy, population, energy supply, energy intensity, weather, and related energy transformation policies. Among them, terminal energy consumption data refers to the energy obtained at the entrance of terminal energy-consuming equipment, which is equal to the primary energy consumption minus the energy losses and consumption in the three intermediate links of energy processing, conversion and storage and transportation, and is one of the components of total energy consumption. Energy intensity refers to the ratio of energy consumption to output, which is used to measure the comprehensive energy utilization efficiency of different economies, and can also be used to compare the degree of dependence of economic development of different economies on energy. Its rough estimation method can be divided by the consumption of crude oil by the total GDP at comparable prices. As long as GDP growth is faster than energy consumption growth, energy intensity will decline.

[0045] In the energy demand forecasting of each industry, the present invention considers the different influencing factors of each industry and the different degrees of influence of each influencing factor, and establishes forecast sub-models for different industries based on the characteristics of each industry, so that each industry can obtain accurate forecast results, and the sum of the forecast data of each industry is the forecast total demand of the forecast area. Among them, different industries can be divided into heating departments, power generation departments, hydrogen production departments, living departments and production departments according to energy consumption departments.

[0046] For example, in the forecast of the total annual demand of the living sector, the urban living energy demand shows a certain correlation with the GDP growth rate, and its forecast model can be based on the fixed energy demand. Uh Function to express:

[0047] DE Uh,e,r,t =DE Uh,e,r,t-1 ×f Uh (GDPR r,t )

[0048] Among them, DE Uh,e,r,t It represents the predicted demand for urban living energy in a certain forecast area in year t, DE Uh,e,r,t-1 represents the demand in year t-1, GDPR r,t represents the economic growth rate of a certain predicted region in year t, f Uh (GDPR r,t ) indicates GDPR r,t The fixed function of .

[0049] Rural life energy demand has a certain correlation with GDP growth rate, but has a different correlation with urban economic growth. Different fixed energy functions f can be used. Rh express:

[0050] DE Rh,e,r,t =DE Rh,e,r,t-1 ×f Rh (GDPR r,t )

[0051] Among them, DE Rh,e,r,t It represents the predicted demand for rural living energy in a certain forecast area in year t, DE Rh,e,r,t-1 represents the demand in year t-1, GDPR r,t represents the economic growth rate of a certain predicted region in year t, f Uh (GDPR r,t ) indicates GDPR r,t The fixed function of .

[0052] Specifically, the total energy demand of each forecast region and industry is decomposed into two factors: economic total and energy intensity, and the industry annual forecast sub-model is constructed. The industry annual forecast sub-model predicts the total annual demand of the industry based on the terminal energy consumption data of each industry and the factors affecting energy demand.

[0053] In the present invention, the first layer of the prediction model predicts on an annual basis, for example, inputting the historical annual terminal energy consumption data of a certain area to be tested for several consecutive years, and at the same time inputting the energy demand influencing factors of the predicted industry in the predicted year, including the annual GDP growth rate and the energy intensity reduction rate. The energy demand influencing factors of the predicted year are future data, which can be obtained by reasonable prediction or formulation of indicators. The data is input into the industry annual prediction sub-model of each corresponding industry of the energy demand prediction model, and the industry annual prediction sub-model outputs the total demand of each industry in the predicted year. The prediction year can be a continuous planning period in the future, such as the prediction year of 2025 to 2030, then the input historical annual terminal energy consumption data is the data of the years before 2025, the model predicts on an annual basis, first predicts the data of 2025, then adds the predicted value of 2025 to the historical annual data, obtains the corresponding annual GDP growth rate and energy intensity reduction rate of 2025, and then predicts 2026, until the prediction of 2030 is completed.

[0054] The energy type decomposition sub-model decomposes the results of the industry forecast sub-model based on the energy substitution coefficient to obtain the forecast demand of each energy type, including electricity, coal, natural gas, oil, and bioenergy.

[0055] The energy substitution coefficient is the amount required for an industry to use one energy source to replace another energy source. For example, when electric vehicles are used to replace fuel vehicles, the relationship between the increase in electricity demand and the decrease in oil demand is expressed as: SB Tr,PO,ELE,t =SB Tr,ELE,PO,t ×SC Tr,ELE,PO , where SB Tr,PO,ELE,t The substitution coefficient, SB, represents the relationship between the increase in electricity demand and the decrease in oil demand. Tr,ELE,PO,t The substitution coefficient, SC, represents the relationship between the increase in oil demand and the decrease in electricity demand. Tr,ELE,PO The substitution coefficient can be used to express the relationship between the increase in electricity demand and the decrease in oil demand.

[0056] The energy type decomposition sub-model is expressed as:

[0057]

[0058] Among them, DE pr,e,r,t represents the total annual demand for energy e by industry r in the forecast region pr in the forecast year t, DE pr,e,r,t-1 represents the total annual demand for energy e by industry r in year t-1, GDPRpr,r,t It represents the GDP growth rate of industry r in the forecast region pr in the forecast year t, IDR pr,r,t represents the energy intensity reduction rate of industry r in forecast region pr in forecast year t, SB pr,ee,e,t SB represents the amount of energy ee substituted by another energy e in the forecast region pr and industry t in the forecast year. pr,e,ee,t It represents the amount of substitution of one energy source e for another energy source ee in the forecast region pr and the forecast year t industry r.

[0059] The monthly decomposition sub-model uses seasonal fluctuation factors and industry-based superposition to decompose. Based on the seasonal fluctuation factors, the forecast results of the energy type decomposition sub-model are decomposed by month to obtain the monthly demand of each energy type. The monthly decomposition sub-model is expressed as:

[0060]

[0061] Among them, DE ELE,r,t,m represents the energy demand of industry r in forecast region pr in the mth month of forecast year t, DE pr,ELE,r,t represents the demand for energy e by the production sector in the forecast region pr in the forecast year t, DE Ho,ELE,r,t represents the energy demand of the living sector in the forecast region pr in the forecast year t, MF Ho,ELE,r,m represents the seasonal fluctuation factor of the electricity demand of the living sector in the mth month affected by the season, ∑ m MF Ho,ELE,r,m =1,DE Hp,ELE,r,t,m represents the energy demand of the hydrogen production sector in the forecast region pr in the mth month of the forecast year t.

[0062] Coal demand includes the demand of heating sector, power generation sector, hydrogen production sector and living sector. Based on the above decomposition model, DE is defined coal,r,t,m is the monthly coal demand, then:

[0063]

[0064] Among them, DE Eg,Coal,r,t,m represents the demand for coal in the heating sector of the forecast region in the forecast year t, DE Hg,Coal,r,t,m represents the demand for coal in the power generation sector in the forecast region in the forecast year t, DE Ho,Coal,r,t,m represents the demand for coal by the living sectors in the forecast area in the forecast year t, DE Hp,Coal,r,t,m represents the demand for coal in the hydrogen production sector in the forecast region in the forecast year t, DE pr,Coal,r,t represents the demand for coal by the production sector in the forecast region pr in the forecast year t, MF Hg,Coal,r,mThe seasonal fluctuation factor of coal demand in the power generation sector in the mth month affected by the season, MF Ho,Coal,r,m It represents the seasonal fluctuation factor of coal demand in the living sector in the mth month affected by seasons.

[0065] 2. Energy demand forecasting for multiple industries and time scales.

[0066] 2.1. Obtain forecast data, including the terminal energy consumption data of the forecast area (province) in historical years and the energy demand influencing factors of the forecast area in the forecast year.

[0067] Energy demand influencing factors that affect energy consumption include economy, population, energy supply, energy intensity, weather, and energy substitution coefficient. The energy substitution coefficient can be obtained based on the analysis of relevant energy transformation policies. Both the terminal energy consumption data and energy demand influencing factors are differentiated into different industries, that is, according to the energy consumption department, it can be divided into heating department, power generation department, hydrogen production department, living department and production department.

[0068] 2.2. Input the obtained terminal energy consumption data and energy demand influencing factors for different industries into the pre-built energy demand forecasting model to obtain the total annual demand, energy type demand and monthly demand of the industry in the forecast area in the forecast year.

[0069] Among them, the industry annual forecast sub-model is used to predict the total annual demand of the industry based on the terminal energy consumption data and energy demand influencing factors of each industry, and the energy type decomposition sub-model is used to decompose the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry, and the monthly decomposition sub-model is used to decompose the energy type demand based on the seasonal fluctuation factor to obtain the monthly demand of each energy type. The energy demand forecasting model and its sub-models are shown in the first part.

[0070] Furthermore, the energy type decomposition sub-model decomposes the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry. The prediction process is expressed as:

[0071]

[0072] Among them, DE pr,e,r,t represents the total annual demand for energy e by industry r in the forecast region pr in the forecast year t, DE pr,e,r,t-1 represents the total annual demand for energy e by industry r in year t-1, GDPR pr,r,t It represents the GDP growth rate of industry r in the forecast region pr in the forecast year t, IDR pr,r,t represents the energy intensity reduction rate of industry r in forecast region pr in forecast year t, SB pr,ee,e,tSB represents the amount of energy ee substituted by another energy e in the forecast region pr and industry t in the forecast year. pr,e,ee,t express…….

[0073] The model further decomposes energy demand into monthly demand based on the differences in seasonal fluctuation characteristics of energy demand in various industries.

[0074] The total electricity demand includes terminal electricity demand and hydrogen production electricity demand, and the hydrogen production electricity demand comes from the results of the hydrogen energy sub-model. Among the terminal electricity demand, the electricity demand of the production sector is mainly affected by economic growth, and it is assumed that it has no fixed seasonal fluctuations. The electricity demand of the living sector is greatly affected by seasonal changes, which is reflected in the cooling demand in summer and the heating demand in winter. Therefore, the fluctuation factor MF is used to describe the seasonal fluctuations in different regions, and the monthly electricity demand of each region can be obtained:

[0075] Furthermore, the monthly decomposition sub-model decomposes the energy demand based on the seasonal fluctuation factor to obtain the monthly demand of each energy type. The prediction process is expressed as:

[0076]

[0077] Among them, DE ELE,r,t,m represents the electricity demand of industry r in forecast region pr in the mth month of forecast year t, DE pr,ELE,r,t represents the electricity demand of the production sector of the forecast region pr for energy source e in the forecast year t, DE Ho,ELE,r,t represents the electricity demand of the living sectors in the forecast region pr in the forecast year t, MF Ho,ELE,r,m The seasonal fluctuation factor of the electricity demand of the living sector in the mth month affected by the season, DE Hp,ELE,r,t,m represents the electricity demand of the hydrogen production sector in the forecast region pr in the mth month of the forecast year t.

[0078] Coal demand includes the demand of heating sector, power generation sector, hydrogen production sector, living sector and production sector. Among them, the monthly coal demand of power generation sector comes from the results of power sub-model, and the monthly coal demand can be obtained:

[0079]

[0080] Among them, DE Eg,Coal,r,t,m represents the demand for coal in the heating sector of the forecast region in the forecast year t, DE Hg,Coal,r,t,m represents the demand for coal in the power generation sector in the forecast region in the forecast year t, DE Ho,Coal,r,t,m represents the demand for coal by the living sectors in the forecast area in the forecast year t, DE Hp,Coal,r,t,m represents the demand for coal in the hydrogen production sector in the forecast region in the forecast year t, DE pr,Coal,t,trepresents the demand for coal by the production sector in the forecast region pr in the forecast year t, MF Hg,Coal,r,m The seasonal fluctuation factor of coal demand in the power generation sector in the mth month affected by the season, MF Ho,Coal,r,m It represents the seasonal fluctuation factor of coal demand in the living sector in the mth month affected by seasons.

[0081] The monthly demand breakdown for natural gas is similar to that for coal, with DE defined as PO,r,t,m is the monthly natural gas demand, then:

[0082] DE PO,r,t,m =DE PO,r,t / 12

[0083] To summarize, the terminal energy demand forecasting model first calculates the demand for each year, province, industry, and energy type, and then further decomposes it into monthly demand on the one hand, and on the other hand, it can be summed up into the total demand of the industry, province, and country.

[0084] Compared with the prior art, the beneficial effects of the present invention are as follows: starting from economic growth and energy intensity, the demand for each year, province, industry, and energy type in the test area is decomposed into monthly demand, which better reflects the impact of policy transformation on the terminal energy consumption structure of a province or industry, including the penetration rate of emission reduction technology deployment, such as the promotion of electric vehicles, the advancement of coal-to-electricity and coal-to-gas, etc. The outlook for economic growth and energy intensity has a great impact on the total energy demand in the future, but no organization has yet given a provincial and industry-specific outlook report. This solution will assist relevant institutions in making provincial and industry-specific outlook reports, and provide data guidance for decision makers to achieve carbon peak and carbon neutrality goals, plans, and policy formulation.

[0085] Furthermore, the S province was predicted by the above prediction method of the present invention.

[0086] First, we obtain historical data of Province S, including GDP and terminal consumption data of energy categories for each industry in the historical years of the region to be tested, as well as assumptions about GDP growth rate, energy intensity and transformation policies for each industry in future years.

[0087] The obtained data is input into the terminal energy demand forecasting model constructed according to the aforementioned embodiment to obtain the total annual demand for terminal energy of each industry in Province S.

[0088] Secondly, based on the total annual energy demand, the annual demand for each energy type is broken down.

[0089] Province S will show a clear trend towards full electrification in the future (e.g. Figure 2 , Figure 3As shown in the figure, the utilization rate of zero-carbon emission energy such as biomass and hydrogen (classified as "other" energy in the figure) has increased significantly.

[0090] In the baseline scenario (e.g. Figure 2 ), the total terminal energy consumption in S Province is expected to peak in 2035, with a peak of about 198 million tons of standard coal, and then enter a stable decline stage. This process is accompanied by the in-depth implementation of strategies such as "replacing coal with electricity" and "replacing oil with electricity". The electrification rate will steadily increase from 23% in 2020 to 64% in 2060, and the energy structure will be significantly optimized.

[0091] In the accelerated development scenario (e.g. Figure 3 ), the peak of total terminal energy consumption also occurs around 2035, but its peak level is slightly higher than the baseline scenario, reaching 209 million tons of standard coal. Between 2035 and 2050, thanks to technological progress and increased energy-saving efforts, energy intensity has dropped significantly, and total terminal energy consumption has decreased by 24% in total (in comparison, the baseline scenario only decreased by 16% during the same period). Since then, the rate of decline has slowed down. Under this scenario, the electrification rate has reached 64% in 2050, which is equivalent to the baseline scenario in 2060. Between 2050 and 2060, with the rapid deployment and application of hydrogen energy technology, the growth rate of terminal electrification has slowed down slightly, reaching 68% in 2060.

[0092] In summary, this plan will assist relevant institutions in making outlook reports by province and industry, and provide data guidance for decision makers in formulating carbon peak and carbon neutrality targets, plans and policies.

[0093] The embodiment of the present invention also provides a terminal energy demand prediction device for multiple industries and multiple time scales, such as Figure 4 As shown, including:

[0094] The data acquisition module 100 is used to acquire the terminal energy consumption data of the forecast area in the historical year and the energy demand influencing factors of the forecast area in the forecast year, wherein the terminal energy consumption data and the energy demand influencing factors are distinguished from different industries;

[0095] An energy demand forecasting model 200, including an industry annual forecasting sub-model 201, an energy type decomposition sub-model 202, and a monthly decomposition sub-model 203;

[0096] The annual prediction sub-model 201 is used to predict the total annual demand of each industry based on the terminal energy consumption data and energy demand influencing factors of each industry;

[0097] The energy type decomposition sub-model 202 is used to decompose the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry;

[0098] The monthly decomposition sub-model 203 is used to decompose the energy type demand based on the seasonal fluctuation factor to obtain the monthly demand of each energy type.

[0099] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory, and the number of processors may be one or more. The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and modules. The processor executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory, so as to implement the terminal energy demand forecasting method for multiple industries and multiple time scales of any of the above embodiments of the present invention.

[0100] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the terminal energy demand forecasting method for multiple industries and multiple time scales of any embodiment of the present invention.

[0102] An embodiment of the present invention further provides a computer program product. When the computer program product runs on a computer, the computer executes the terminal energy demand forecasting method for multiple industries and multiple time scales of any of the above embodiments of the present invention.

[0103] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-industry and multi-timescale terminal energy demand forecasting method, characterized by: include: Acquire the terminal energy consumption data of the forecast area in the historical years and the energy demand influencing factors of the forecast area in the forecast year, wherein the terminal energy consumption data and the energy demand influencing factors are distinguished from different industries; Input the terminal energy consumption data and energy demand influencing factors of each industry into a pre-built energy demand forecasting model to obtain the total annual demand, energy type demand and monthly demand of the forecast area in the forecast year; Among them, the energy demand forecasting model is constructed from bottom to top using the factor decomposition method, the upper layer is the industry annual forecasting sub-model, the middle layer is the energy type decomposition sub-model, and the lower layer is the monthly decomposition sub-model; the industry annual forecasting sub-model is based on the terminal energy consumption data and energy demand influencing factors of each industry to obtain the total annual demand of the industry, the energy type decomposition sub-model decomposes the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry, and the monthly decomposition sub-model decomposes the energy type demand based on the seasonal fluctuation factor to obtain the monthly demand of each energy type.

2. The method for predicting terminal energy demand for multiple industries and multiple time scales according to claim 1 is characterized in that: The energy demand influencing factors include GDP growth rate, energy intensity and energy substitution coefficient, and the energy substitution coefficient is obtained based on energy transformation policy prediction.

3. The method for predicting terminal energy demand for multiple industries and multiple time scales according to claim 1 is characterized in that: The energy type decomposition sub-model is expressed as: Among them, DE pr，e,r，t represents the total annual demand for energy e by industry r in the forecast region pr in the forecast year t, DE pr，e，r，t-1 represents the total annual demand for energy e by industry r in year t-1, GDPR pr，r，t It represents the GDP growth rate of industry r in the forecast region pr in the forecast year t, IDR pr，r，t represents the energy intensity reduction rate of industry r in forecast region pr in forecast year t, SB pr，ee，e，t SB represents the amount of energy ee substituted by another energy e in the forecast region pr and industry t in the forecast year. pr,e，ee，t It represents the amount of substitution of one energy source e for another energy source ee in the forecast region pr and in the forecast year t industry r.

4. The method for predicting terminal energy demand for multiple industries and multiple time scales according to claim 3 is characterized in that: The energy types include: electricity, coal, natural gas, oil and bioenergy.

5. The method for predicting terminal energy demand for multiple industries and multiple time scales according to claim 3 is characterized in that: The industries are divided into: heating sector, power generation sector, hydrogen production sector, living sector and production sector.

6. The method for predicting terminal energy demand for multiple industries and multiple time scales according to claim 3 is characterized in that: The monthly decomposition sub-model is expressed as: Among them, DE ELE，r，t，m represents the energy demand of industry r in forecast region pr in the mth month of forecast year t, DE pr，ELE,r，t represents the demand for energy e by the production sector in the forecast region pr in the forecast year t, DE Ho，ELE,r，t represents the energy demand of the living sector in the forecast region pr in the forecast year t, MF Ho，ELE,r，m represents the seasonal fluctuation factor of the electricity demand of the living sector in the mth month affected by the season, ∑ m MF Ho，ELE,r，m =1,DE Hp，ELE,r,t，m represents the energy demand of the hydrogen production sector in the forecast region pr in the mth month of the forecast year t.

7. A terminal energy demand forecasting device for multiple industries and time scales, characterized in that: include: A data acquisition module, used to acquire the terminal energy consumption data of the forecast area in the historical year, and the energy demand influencing factors of the forecast area in the forecast year, wherein the terminal energy consumption data and the energy demand influencing factors are distinguished from different industries; Energy demand forecasting model, including industry annual forecasting sub-model, energy type decomposition sub-model and monthly decomposition sub-model; The annual forecast sub-model is used to predict the total annual demand of each industry based on the terminal energy consumption data and energy demand influencing factors of each industry; The energy type decomposition sub-model is used to decompose the total annual demand of the industry based on the energy substitution coefficient to obtain the energy type demand of each industry; The monthly decomposition sub-model is used to decompose the demand for the energy types based on seasonal fluctuation factors to obtain the monthly demand for each energy type.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the multi-industry and multi-timescale terminal energy demand forecasting method described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the multi-industry and multi-timescale terminal energy demand forecasting method described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the computer program product runs on a computer, it enables the computer to implement the multi-industry and multi-timescale terminal energy demand forecasting method as described in any one of claims 1 to 6.

Images