Electricity and coal consumption prediction method, device and equipment and storage medium

Abstract

The invention provides an electricity and coal consumption prediction method and device, equipment and a storage medium, and the method comprises the steps: inputting a total production value into a total electricity consumption regression model, obtaining a total electricity consumption prediction value, inputting the total electricity consumption prediction value into a total power generation regression model, and obtaining a total power generation prediction value; counting the historical average value of the average utilization hours of the clean energy except the water and electricity as the average utilization hours corresponding to the clean energy except the water and electricity; inputting the average precipitation into a hydropower regression model to obtain an average utilization hour corresponding to hydropower; calculating each clean energy generating capacity predicted value based on the average utilization hour, and subtracting all the clean energy generating capacity predicted values from the total generating capacity predicted value to obtain a thermal power generating capacity predicted value; using a time sequence method to predict the proportion of the coal power in the thermal power generation amount, and using the proportion in the thermal power generation amount prediction value as the coal power generation amount prediction value; and based on the predicted value of the coal power generation capacity and the power generation coal consumption, calculating to obtain a predicted value of power-coal consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of power system prediction, and in particular to a method, device, equipment and storage medium for predicting power coal consumption. Background Art

[0002] Power coal accounts for 50% to 60% of my country's total coal consumption and is the main body of coal consumption. Therefore, its consumption volume is the basis for supply demand analysis and is crucial to ensuring the supply of energy and electricity.

[0003] Among the related technologies, the existing coal consumption forecasting methods mainly include time series method, regression analysis method, expert experience method, etc. The time series method is only based on the temporal characteristics of the historical data of power coal consumption, and does not consider the impact of changes in influencing factors on coal consumption. In addition, the existing regression analysis method does not systematically consider multiple influencing factors such as economic development, climate conditions, new energy development, and installed capacity growth. In addition, the existing methods mainly predict coal consumption, and there are few specialized methods for predicting coal for power generation.

[0004] Based on the above analysis of the development status of this technical field, the existing technical solutions lack the concept of average utilization hours to eliminate the impact of installed capacity growth. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, equipment and storage medium for predicting power coal consumption, aiming to solve the above-mentioned problems in the prior art.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a method for predicting power coal consumption, comprising:

[0007] The gross domestic product is input into the total electricity consumption regression model to obtain the total electricity consumption forecast value, and the total electricity consumption forecast value is input into the total power generation regression model to obtain the total power generation forecast value;

[0008] Calculate the historical average of the average utilization hours of each clean energy source except hydropower as the corresponding average utilization hours of each clean energy source except hydropower; calculate the average precipitation in the region, input the average precipitation into the hydropower regression model, and obtain the corresponding average utilization hours of hydropower;

[0009] Calculate the predicted value of power generation of each clean energy source based on the average utilization hours, subtract all the predicted values ​​of power generation of clean energy sources from the predicted value of total power generation to obtain the predicted value of thermal power generation;

[0010] The time series method is used to predict the proportion of coal-fired power generation in thermal power generation, and the proportion in the thermal power generation forecast is used as the coal-fired power generation forecast; based on the coal-fired power generation forecast and the coal consumption for power generation, the regional power coal consumption forecast is calculated.

[0011] According to a second aspect of an embodiment of the present invention, there is provided a device for predicting power coal consumption, comprising:

[0012] The total amount prediction module is used to input the gross production value into the total electricity consumption regression model to obtain the total electricity consumption prediction value, and input the total electricity consumption prediction value into the total power generation regression model to obtain the total power generation prediction value;

[0013] The average utilization hour calculation module is used to calculate the historical average of the average utilization hours of each clean energy source except hydropower as the average utilization hours corresponding to each clean energy source except hydropower; calculate the average precipitation in the region, input the average precipitation into the hydropower regression model, and obtain the average utilization hours corresponding to hydropower;

[0014] The thermal power generation prediction module is used to calculate the predicted value of each clean energy power generation based on the average utilization hours, and subtract all the clean energy power generation predicted values ​​from the total power generation predicted value to obtain the thermal power generation predicted value;

[0015] The power coal consumption forecasting module is used to use the time series method to predict the proportion of coal-fired power generation to thermal power generation, and take the proportion in the thermal power generation forecast value as the coal-fired power generation forecast value; based on the coal-fired power generation forecast value and the coal consumption for power generation, the power coal consumption forecast value of the region is calculated.

[0016] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for predicting power coal consumption as provided in the first aspect of the present disclosure are implemented.

[0017] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of the method for predicting power coal consumption provided in the first aspect of the present disclosure are implemented.

[0018] The technical solution provided by the embodiment of the present invention includes the following beneficial effects: the predicted value of power generation of each clean energy is calculated based on the average utilization hours to take into account the changes in installed capacity caused by new commissioning, retirement, etc., and the average utilization hour calculation method that matches each clean energy is selected according to the characteristics of different clean energy sources, among which hydropower energy is obtained based on the regression model of average precipitation; in the prediction process of the predicted value of power coal consumption, the coal consumption for power generation is taken into account, so that the result of the predicted value of power coal consumption is more accurate.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 is a flow chart of a method for predicting power coal consumption according to an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of a device for predicting power coal consumption according to an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0025] Method Embodiment

[0026] According to an embodiment of the present invention, a method for predicting power coal consumption is provided. Figure 1 Flow chart of the method for predicting power coal consumption according to an embodiment of the present invention, to predict power coal consumption in the next few years, such as Figure 1 As shown, the method for predicting power coal consumption according to an embodiment of the present invention specifically includes:

[0027] In step S110, the gross output value is input into the total power consumption regression model to obtain the total power consumption forecast value, and the total power consumption forecast value is input into the total power generation regression model to obtain the total power generation forecast value, which specifically includes:

[0028] From the perspective of the driving effect of economic growth on electricity demand, the total electricity consumption driven by unit GDP growth has been on an upward trend in recent years, and the relative error between the total electricity consumption and total power generation in the country is within 1.5%. Therefore, an electricity regression model between gross domestic product and total electricity consumption, as well as a power generation regression model between total electricity consumption and total power generation are established in advance;

[0029] Obtain the pre-forecasted gross domestic product, which is provided by a professional department. In the embodiment of the present invention, it can be determined according to the expected target of GDP growth in the department report. The total power consumption forecast value is calculated by the total power consumption regression model of Formula 1, and the total power generation forecast value is calculated by the total power generation regression model of Formula 2:

[0030]

[0031] in, represents the total electricity consumption forecast value, G represents the gross regional product, and They represent the regression coefficients, represents the total power generation forecast value, and They represent the regression coefficients, and It can be calculated by the least squares method based on historical data for the same period.

[0032] If the region is set to the whole country, the total power generation forecast for 2024 is 986.03 billion kWh.

[0033] In step S120, the historical average of the average utilization hours of each clean energy source except hydropower is calculated as the average utilization hours corresponding to each clean energy source except hydropower; the average precipitation is input into the hydropower regression model to obtain the average utilization hours corresponding to hydropower, wherein the average utilization hours is the ratio of power generation to the average capacity of power generation equipment, specifically including:

[0034] In order to exclude the impact of installed capacity growth, the impact of wind and solar resources on power generation is studied separately, and the average utilization hours are introduced. The theory is shown in Formula 8:

[0035] H i =E i / P i Formula 8;

[0036] Among them, H i represents the theoretical average utilization hours of clean energy i, E i represents the power generation of clean energy i, which refers to the power generation for the whole year, P i Represents the average capacity of the power generation equipment of clean energy i. The average capacity of power generation equipment refers to the capacity of the power generation unit calculated on average by calendar time during the reporting period. Taking into account the changes in installed capacity caused by new commissioning and retirement, it is calculated as the average value of the installed capacity in the initial period and the final period. In this invention, the average value of the initial and final installed capacity is used as the average capacity of the power generation equipment during the period for the first time. The unit of capacity is kilowatt-hour.

[0037] In the embodiment of the present invention, clean energy needs to consider hydropower, wind power, solar energy and nuclear power. Since the average utilization hours of hydropower are greatly affected by the annual precipitation, and the annual precipitation in the region is not easy to be stable; the average utilization hours of other clean energy sources are relatively stable. In recent years, the average utilization hours of wind power have fluctuated between 1900 and 2200, and the average utilization hours of solar energy have fluctuated between 1140 and 1230. Therefore, the average historical hours of wind power, solar energy and nuclear power are determined by their corresponding average values ​​of the same period, while hydropower adopts a regression model method;

[0038] Calculate the average precipitation. The average precipitation can be obtained based on climate prediction. The region can be divided into M sub-regions according to climate differences. For sub-region j, its average precipitation in the same period of the year is R j , climate prediction can directly provide the deviation of sub-region j from the average precipitation in the same period during the forecast period, and can also clearly define the percentage of the sub-region in the total land area of ​​the total region, and use formula 3 to calculate the average precipitation of the region:

[0039]

[0040] Among them, R represents the average precipitation in the region, j represents the subscript to distinguish the subregions, M represents the number of subregions, and R j represents the precipitation in sub-region j during the same period, L% represents the precipitation deviation in sub-region j, and k% represents the land area proportion in sub-region j.

[0041] Taking into account the difference in seasonal precipitation, the precipitation in the second to fourth quarters does not change much compared with the same period, and can be directly obtained by the average value of the same period. The average utilization hours of hydropower are calculated by the hydropower regression model of formula 4:

[0042]

[0043] Among them, H h represents the average utilization hours of hydropower, R represents the average precipitation, and They represent regression coefficients respectively, and the formula 4 used in the embodiment of the present invention is Hh=5.12R+147.62;

[0044] Step 1: So far, the average utilization hours of hydropower, wind power, solar power and nuclear power have been obtained.

[0045] In step S130, the predicted value of power generation of each clean energy is calculated based on the average utilization hours, and all the predicted values ​​of power generation of clean energy are subtracted from the predicted value of total power generation to obtain the predicted value of thermal power generation, which specifically includes:

[0046] Get the initial installed capacity during each clean energy forecast period, the initial installed capacity P i SUsually obtained directly from survey statistics; the final installed capacity P i T It is obtained by solving the pre-established optimization model, where the optimization model takes the minimum installed cost as the goal, and the solution variable is the final installed capacity of various power sources including clean energy. Since electricity needs to be balanced, the optimization model also includes the final installed capacity of non-clean energy. The objective function of the optimization model is shown in Formula 9:

[0047]

[0048] Among them, c i represents the unit capacity installation cost of clean energy i, c th represents the unit capacity installation cost of non-clean energy, represents the final installed capacity of non-clean energy;

[0049] The constraints of the optimization model include installed capacity resource constraints, investment cost constraints, and power balance constraints;

[0050] The installed resource constraints are shown in formulas 10 and 11:

[0051]

[0052]

[0053] Among them, P i max and P i min They represent the maximum and minimum final installed capacity of clean energy i, respectively. The above thresholds are determined according to resource conditions such as water, wind, and light; and They represent the maximum and minimum values ​​of the final installed capacity of non-clean energy i, respectively. The above thresholds are determined according to the corresponding resource conditions;

[0054] The investment cost constraints are shown in equations 12 and 13:

[0055]

[0056]

[0057] in, and Represent the maximum and minimum values ​​of clean energy investment costs, respectively. and They represent the maximum and minimum investment costs of non-clean energy, respectively. The above thresholds are determined based on investment capacity, investment willingness and other conditions. represents the initial installed capacity of non-clean energy;

[0058] The power balance constraint is shown in formula 14:

[0059]

[0060] Among them, η i represents the effective power generation coefficient of clean energy i. Conventional hydropower takes 60%-80% in summer and 40%-60% in winter. Pumped storage takes 90%-100%. Nuclear power takes 100%. Wind power takes 5%-15%. Solar power takes 0%. η th Indicates the effective power generation coefficient of non-clean energy, generally 80%-95%; It represents the maximum power load, which can be considered separately according to seasons. λ represents the reserve rate, which is usually 3%-5%;

[0061] After solving the optimization model, we get P i T and Due to the power balance constraint, the objective function of the optimization model has a non-clean energy-related design, but only P i T For subsequent calculations;

[0062] Use Formula 5 to calculate the predicted value of each clean energy power generation:

[0063] E f i = (P i S +P i T ) / 2 × H a i Formula 5;

[0064] Among them, E f i represents the predicted value of power generation corresponding to clean energy i, where the subscript i includes hydropower, wind power, solar power and nuclear power, P i S represents the initial installed capacity of clean energy i during the forecast period, P i T represents the final installed capacity of clean energy i during the forecast period, H a i Indicates the average utilization hours of clean energy i, that is, the calculation result of the historical average. In the embodiment of the present invention, the initial installed capacity and the final installed capacity are obtained from the results provided by the professional department, the predicted value of hydropower generation is 1374.9 billion kWh, the predicted value of wind power generation is 1046.6 billion kWh, the predicted value of solar power generation is 842.6 billion kWh, and the predicted value of nuclear power generation is 461.5 billion kWh.

[0065] The predicted value of thermal power generation is obtained by formula 15:

[0066]

[0067] in, represents the predicted value of thermal power generation, represents the total power generation forecast value, and They respectively represent the predicted power generation values ​​of hydropower, wind power, solar power and nuclear power. In the embodiment of the present invention, the predicted power generation value of thermal power is 613.46 billion kWh.

[0068] In step S140, the proportion of coal-fired power generation to thermal power generation is predicted using the time series method, and the proportion in the thermal power generation prediction value is used as the coal-fired power generation prediction value; based on the coal-fired power generation prediction value and the power generation coal consumption, the power coal consumption prediction value is calculated, specifically including:

[0069] Obtain the proportion of coal-fired power generation to thermal power generation in historical years as a sequence, and the proportion in the sequence shows a downward trend;

[0070] Based on the sequence, the ARIMA time series method is used to predict the proportion, that is, to predict the changing trend of the proportion. The ARIMA model combines three statistical models, including: autoregression AR, difference I and moving average MA, which can directly predict the proportion of future years based on the historical proportion sequence.

[0071] Use Formula 6 to calculate the forecast value of coal-fired power generation:

[0072]

[0073] in, represents the predicted value of thermal power generation, Represents the forecast value of coal-fired power generation, in kilowatt-hours, l f Represents the predicted proportion.

[0074] Use Formula 7 to calculate the forecast value of power coal consumption:

[0075]

[0076] in, represents the forecast value of power coal consumption, e f c It represents the coal consumption for power generation in grams per kilowatt-hour. The coal consumption for power generation adopts the recent statistical value.

[0077] To sum up, in response to the existing problems, the method for predicting power coal consumption invented this time calculates the predicted value of power generation of each clean energy based on the average utilization hours, so as to take into account the changes in installed capacity caused by new commissioning and retirement, and selects the average utilization hour calculation method that matches each clean energy according to its characteristics. Among them, hydropower energy is affected by precipitation, so its average utilization hours are obtained based on the regression model of average precipitation, while other clean energy sources are relatively stable and are obtained based on the historical average values ​​of the same period, so as to further obtain the predicted value of thermal power generation; in the prediction process of the power coal consumption prediction value, the coal consumption for power generation is taken into account, so that the result of the power coal consumption prediction value is more accurate.

[0078] Device Embodiment

[0079] According to an embodiment of the present invention, a device for predicting power coal consumption is provided. Figure 2 Schematic diagram of a device for predicting power coal consumption according to an embodiment of the present invention. Figure 2 As shown, the power coal consumption prediction device according to the embodiment of the present invention specifically includes:

[0080] The total amount prediction module 20 is used to input the gross production value into the total electricity consumption regression model to obtain the total electricity consumption prediction value, and input the total electricity consumption prediction value into the total power generation regression model to obtain the total power generation prediction value, which is specifically used for:

[0081] Obtain the pre-forecasted gross production value, calculate the total electricity consumption forecast value through the total electricity consumption regression model of Formula 1, and calculate the total power generation forecast value through the total power generation regression model of Formula 2:

[0082]

[0083]

[0084] in, represents the total electricity consumption forecast value, G represents the gross domestic product, and They represent the regression coefficients, represents the total power generation forecast value, and They represent regression coefficients respectively.

[0085] The average utilization hour calculation module 22 is used to calculate the historical average of the average utilization hours of each clean energy source except hydropower as the average utilization hours corresponding to each clean energy source except hydropower; calculate the average precipitation in the region, input the average precipitation into the hydropower regression model, and obtain the average utilization hours corresponding to hydropower, which is specifically used for:

[0086] Divide the region into sub-regions and use Formula 3 to calculate the average precipitation in the region:

[0087]

[0088] Among them, R represents the average precipitation in the region, j represents the subscript to distinguish the subregions, M represents the number of subregions, and R j represents the common precipitation in sub-region j during the same period, L% represents the precipitation deviation in sub-region j, and k% represents the land area share of sub-region j;

[0089] The average precipitation is input into Formula 4, and the average utilization hours of hydropower are calculated by the hydropower regression model of Formula 4:

[0090]

[0091] Among them, H h represents the average utilization hours of hydropower, and They represent regression coefficients respectively.

[0092] The thermal power generation prediction module 24 is used to calculate the predicted value of each clean energy power generation based on the average utilization hours, and subtract all the clean energy power generation predicted values ​​from the total power generation predicted value to obtain the thermal power generation predicted value, which is specifically used for:

[0093] Obtain the initial installed capacity during each clean energy forecast period, and use an optimization model with the goal of minimizing the installed capacity cost and including constraints to solve the final installed capacity during each clean energy forecast period;

[0094] Based on the initial installed capacity and the final installed capacity, the predicted value of each clean energy power generation is calculated using Formula 5:

[0095]

[0096] in, represents the predicted value of power generation corresponding to clean energy i, where the subscript i includes hydropower, wind power, solar power and nuclear power, P i S represents the initial installed capacity of clean energy i during the forecast period, P i T represents the final installed capacity of clean energy i during the forecast period, H a i Represents the average utilization hours of clean energy i.

[0097] The power coal consumption prediction module 26 is used to predict the proportion of coal-fired power generation to thermal power generation using the time series method, and use the proportion in the thermal power generation prediction value as the coal-fired power generation prediction value; based on the coal-fired power generation prediction value and the power generation coal consumption, the power coal consumption prediction value is calculated, which is specifically used for:

[0098] Get the proportion of coal-fired power generation to thermal power generation in historical years as a sequence;

[0099] Forecast proportions based on the series using the ARIMA time series method.

[0100] Use Formula 6 to calculate the forecast value of coal-fired power generation:

[0101]

[0102] in, represents the predicted value of thermal power generation, represents the predicted value of coal-fired power generation, l f Represents the predicted proportion.

[0103] Use Formula 7 to calculate the forecast value of power coal consumption:

[0104]

[0105] in, represents the forecast value of power coal consumption, e f c Indicates coal consumption for power generation.

[0106] To sum up, in response to the existing problems, the invention of the power coal consumption prediction device calculates the predicted value of power generation of each clean energy based on the average utilization hours, so as to take into account the changes in installed capacity caused by new commissioning and retirement, and selects the average utilization hour calculation method that matches each clean energy according to its characteristics. Among them, hydropower energy is affected by precipitation, so its average utilization hours are obtained based on the regression model of average precipitation, while other clean energy sources are relatively stable and are obtained based on the historical average values ​​of the same period, so as to further obtain the predicted value of thermal power generation; in the prediction process of the power coal consumption prediction value, the power generation coal consumption is taken into account, so that the result of the power coal consumption prediction value is more accurate.

[0107] Electronic device embodiment

[0108] Figure 3 3 is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device 300 may include at least one processor 310 and a memory 320. The processor 310 may execute instructions stored in the memory 320. The processor 310 is connected to the memory 320 through a data bus. In addition to the memory 320, the processor 310 may also be connected to an input device 330, an output device 340, and a communication device 350 through a data bus.

[0109] The processor 310 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0110] The memory 320 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0111] In the embodiment of the present disclosure, executable instructions are stored in the memory 320, and the processor 310 can read the executable instructions from the memory 320 and execute the instructions to implement all or part of the steps of any of the power coal consumption prediction methods in the above exemplary embodiments.

[0112] Computer Readable Storage Medium Embodiments

[0113] In addition to the above-mentioned methods and devices, the exemplary embodiments of the present disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product, wherein the computer product includes computer program instructions, which can be executed by a processor to implement all or part of the steps described in any of the above-mentioned exemplary embodiments in the method for predicting power coal consumption.

[0114] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages ​​and scripting languages ​​(e.g., Python). The program code may be executed entirely on the user computing device, partially on the user computing device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0115] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of readable storage media include: a static random access memory (SRAM) with one or more wires electrically connected, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

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

Claims

1. A method for predicting power coal consumption, characterized in that: include: Inputting the gross output value into the total electricity consumption regression model to obtain a total electricity consumption forecast value, and inputting the total electricity consumption forecast value into the total power generation regression model to obtain a total power generation forecast value; Calculate the historical average of the average utilization hours of each clean energy source except hydropower as the average utilization hours corresponding to each clean energy source except hydropower; calculate the average precipitation in the region, input the average precipitation into the hydropower regression model, and obtain the average utilization hours corresponding to hydropower; Calculating the predicted value of power generation of each clean energy source based on the average utilization hours, and subtracting all the predicted values ​​of power generation of the clean energy sources from the predicted value of total power generation to obtain the predicted value of thermal power generation; The proportion of coal-fired power generation to thermal power generation is predicted using the time series method, and the proportion in the thermal power generation prediction value is used as the coal-fired power generation prediction value; based on the coal-fired power generation prediction value and the coal consumption for power generation, the regional power coal consumption prediction value is calculated.

2. The method according to claim 1, characterized in that The step of inputting the gross output value into the total electricity consumption regression model to obtain the total electricity consumption forecast value, and inputting the total electricity consumption forecast value into the total power generation regression model to obtain the total power generation forecast value specifically includes: Obtain the pre-forecasted gross production value, calculate the total electricity consumption forecast value through the total electricity consumption regression model of Formula 1, and calculate the total power generation forecast value through the total power generation regression model of Formula 2: in, represents the total electricity consumption forecast value, G represents the gross domestic product, and They represent the regression coefficients, represents the total power generation forecast value, and Represent the regression coefficients respectively.

3. The method according to claim 1, characterized in that The average precipitation in the calculation area is input into the hydropower regression model to obtain the average utilization hours corresponding to the hydropower, specifically including: Divide the region into sub-regions and use Formula 3 to calculate the average precipitation in the region: Among them, R represents the average precipitation in the region, j represents the subscript to distinguish the subregions, M represents the number of subregions, and R j represents the common precipitation in sub-region j during the same period, L% represents the precipitation deviation in sub-region j, and k% represents the land area share of sub-region j; The average precipitation is input into Formula 4, and the average utilization hours of hydropower are calculated by the hydropower regression model of Formula 4: Among them, H h represents the average utilization hours of hydropower, and Represent the regression coefficients respectively.

4. The method according to claim 1, characterized in that: The calculation of the predicted value of each clean energy power generation based on the average utilization hours specifically includes: Obtain the initial installed capacity during each clean energy forecast period, and use an optimization model with the goal of minimizing the installed capacity cost and including constraints to solve the final installed capacity during each clean energy forecast period; Based on the initial installed capacity and the final installed capacity, the predicted value of each clean energy power generation is calculated using Formula 5: in, represents the predicted value of power generation corresponding to clean energy i, where the subscript i includes hydropower, wind power, solar power and nuclear power, P i S represents the initial installed capacity of clean energy i during the forecast period, P i T represents the final installed capacity of clean energy i during the forecast period, H a i Represents the average utilization hours of clean energy i.

5. The method according to claim 1, characterized in that The use of the time series method to predict the proportion of coal-fired power generation to thermal power generation specifically includes: Get the proportion of coal-fired power generation to thermal power generation in historical years as a sequence; The proportions are predicted based on the series using the ARIMA time series method.

6. The method according to claim 1, characterized in that The method of using the proportion of the thermal power generation forecast value as the coal power generation forecast value specifically includes: Use Formula 6 to calculate the forecast value of coal-fired power generation: in, represents the predicted value of thermal power generation, represents the predicted value of coal-fired power generation, l f Represents the predicted proportion.

7. The method according to claim 6, characterized in that The calculation of the predicted value of regional power coal consumption based on the predicted value of coal-fired power generation and power generation coal consumption specifically includes: Use Formula 7 to calculate the forecast value of power coal consumption: in, represents the forecast value of power coal consumption, Indicates coal consumption for power generation.

8. A device for predicting power coal consumption, characterized in that: include: A total amount prediction module is used to input the gross production value into a total electricity consumption regression model to obtain a total electricity consumption prediction value, and input the total electricity consumption prediction value into a total power generation regression model to obtain a total power generation prediction value; The average utilization hour calculation module is used to calculate the historical average of the average utilization hours of each clean energy source except hydropower as the average utilization hours corresponding to each clean energy source except hydropower; calculate the average precipitation in the region, input the average precipitation into the hydropower regression model, and obtain the average utilization hours corresponding to hydropower; A thermal power generation prediction module, used to calculate the predicted value of power generation of each clean energy source based on the average utilization hour, and subtract all the predicted values ​​of power generation of clean energy sources from the predicted value of total power generation to obtain the predicted value of thermal power generation; The power coal consumption forecasting module is used to use the time series method to predict the proportion of coal-fired power generation to thermal power generation, and use the proportion in the thermal power generation forecast value as the coal-fired power generation forecast value; based on the coal-fired power generation forecast value and the coal consumption for power generation, the power coal consumption forecast value of the region is calculated.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for predicting power coal consumption as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the method for predicting power coal consumption as described in any one of claims 1 to 7 are implemented.

Images