A method and device for optimal scheduling of energy balance in a province

Abstract

This invention discloses a method and apparatus for optimizing energy balance scheduling at the provincial level, belonging to the field of energy scheduling. The method comprises: predicting electricity consumption for each industry group using a grey prediction model; calculating energy consumption at the city and county levels based on the city and county-level energy consumption structures of each industry; predicting supply based on energy supply weights, energy production, and energy imports; predicting heating and electricity supply based on standard coal consumption for heating and electricity supply, respectively; constructing a two-layer energy scheduling model based on energy consumption and supply at the city and county levels; solving the two-layer energy scheduling model hierarchically using a solver to generate provincial energy scheduling instructions; and controlling the provincial energy network of the target province for energy scheduling based on the provincial energy scheduling instructions. Therefore, by implementing this invention, the accuracy and efficiency of energy supply and demand balance can be significantly improved.

Description

Technical Field

[0001] This invention relates to the field of energy dispatching, and in particular to a method and apparatus for optimizing energy balance dispatching at the provincial level. Background Technology

[0002] Constructing energy balance models is one of the main methods for achieving rapid decomposition, simulation, and balance calculation of regional energy system architecture and evolution paths. However, existing energy balance models have the following problems: First, there is insufficient adaptability to provincial-level applications. For example, mainstream international models (such as MARKAL or LEAP) are mostly designed at a large regional scale, with granularity down to the industry or prefecture-level city level, and do not support county-level data input and output. Second, the default accounting for energy categories is unclear. Existing energy balance models mostly study the total energy consumption and supply, neglecting the characterization of energy supply and demand by type. Third, the depiction of energy transportation flows is vague, lacking effective modeling of energy flow paths and optimal allocation mechanisms between counties and prefecture-level cities. Summary of the Invention

[0003] This invention provides a method and apparatus for optimizing energy balance scheduling at the provincial level, which can realize refined energy scheduling from the provincial level to the county level, and significantly improve the accuracy and scheduling efficiency of energy supply and demand balance.

[0004] This invention provides a provincial energy balance optimization scheduling method, comprising: Electricity consumption is predicted based on the electricity consumption characteristics of various industries over a preset time period. Based on the electricity consumption prediction results and the energy structure of each industry, the provincial energy consumption is calculated. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county. Based on the energy supply weight, energy production and energy import of each district and county, a preliminary forecast of the energy supply of each city and each county is made. Then, the heat supply and power supply are predicted based on the standard coal consumption for heating and standard coal consumption for power supply, and added to the preliminary forecast results to obtain the energy supply of each city and each county. A two-tier energy dispatch model is constructed based on the energy consumption of each city and each county, as well as the energy supply of each city and each county. The two-tier energy dispatch model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints. The two-layer energy dispatch model is solved hierarchically using a solver to generate provincial energy dispatch instructions, and the provincial energy network of the target province is controlled to perform energy dispatch according to the provincial energy dispatch instructions.

[0005] This invention, through industry clustering based on electricity consumption characteristics and a combined prediction model employing grey prediction and ARIMA residual correction, effectively improves the accuracy of electricity consumption prediction for various industries, providing a reliable data foundation for subsequent energy balance calculations. By using an energy conversion method combining trend fitting and electricity substitution correction, it accurately predicts the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand prediction. Through a district / county structure decomposition method using weighted moving smoothing and growth trend correction, it achieves a reasonable spatial allocation of energy consumption, improving the precision of regional energy management. Through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, it scientifically predicts the energy supply of each district / county, providing accurate supply-side data support for energy dispatch. By introducing unit aging rate correction for standard coal consumption prediction in heating and power generation, it accurately reflects equipment efficiency degradation, improving the reliability of heating and power supply capacity prediction. By constructing a district / county-city two-tier energy dispatch model, it achieves hierarchical and regional optimized dispatch, effectively reducing energy transmission costs and improving system operating efficiency. Compared to existing technologies that suffer from unclear default calculations for energy by region and category, this application enables refined energy dispatching from the provincial level down to the county level, significantly improving the accuracy and efficiency of energy supply and demand balance.

[0006] Furthermore, the electricity consumption is predicted based on the electricity consumption characteristics of various industries within a preset time period, and the provincial energy consumption is calculated based on the electricity consumption prediction results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county, including: Based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. Based on the energy consumption of the first province and the energy structure of each industry, energy conversion is performed to obtain the energy consumption of the province. Based on the city and county structure of energy consumption of each industry, the energy consumption of each city and the energy consumption of each county are calculated respectively.

[0007] This invention, through industry clustering based on electricity consumption characteristics and a combined prediction model employing grey prediction and ARIMA residual correction, effectively improves the accuracy of electricity consumption prediction for various industries, providing a reliable data foundation for subsequent energy balance calculations. By using an energy conversion method combining trend fitting and electricity substitution correction, it accurately predicts the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand forecasting. Furthermore, through a city / district / county structure decomposition method using weighted moving smoothing and growth trend correction, it achieves a reasonable spatial allocation of energy consumption, improving the precision of regional energy management.

[0008] Furthermore, based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province, including: Collect the electricity consumption of the first industry in each industry of the target province within the preset time period; Features are extracted from the electricity consumption of each of the first industries to obtain the industry electricity consumption characteristics of each industry; wherein, the industry electricity consumption characteristics include the industry electricity consumption compound growth rate, the industry annual fluctuation range, the industry electricity consumption contribution ratio, and the industry electricity consumption proportion trend characteristics. Based on the electricity consumption characteristics of each industry, the K-Means algorithm is used for clustering to obtain multiple industry groups; wherein, the number of industry groups is determined according to the profile coefficient of each industry. The grey prediction model is used to predict the electricity consumption of each industry group, and the corresponding electricity consumption of multiple first industry groups is obtained. The ARIMA model is used to correct the residuals of the electricity consumption of each first industry group, and the corresponding electricity consumption of multiple industry groups is obtained. Based on the electricity consumption data of each industry group and the proportion of each industry in the corresponding industry group, the industry electricity consumption of each industry is calculated, and the electricity consumption of all industries is added together to obtain the first provincial energy consumption of the target province.

[0009] The embodiments of the present invention can effectively improve the accuracy of electricity consumption prediction by using a combined prediction model of gray prediction and ARIMA residual correction through industry clustering based on electricity consumption characteristics, and provide a reliable data foundation for subsequent energy balance calculations.

[0010] Furthermore, the process of calculating the provincial energy consumption based on the energy consumption of the first province and the energy structure of each industry to obtain the provincial energy consumption includes: The ARIMA model is used to fit the trend of the energy structure of each industry during the preset time period to obtain multiple first energy conversion ratios for each industry; wherein, the first energy conversion ratio corresponds to one of four energy sources: coal, oil, natural gas and heat. Based on the amount of electricity substitution during the preset time period, the conversion ratio of each of the first energy sources is adjusted to obtain multiple energy conversion ratios for each of the industries. Energy consumption is calculated based on the energy consumption of the first province and the energy conversion ratios of each province to obtain the energy consumption of multiple second provinces. The energy consumption of the first province is then added to the energy consumption of each of the second provinces to obtain the energy consumption of the target province.

[0011] The embodiments of the present invention employ an energy conversion method that combines trend fitting with electricity substitution correction, which can accurately predict the consumption structure of multiple energy sources and enhance the comprehensiveness and foresight of energy demand forecasting.

[0012] Furthermore, the calculation of energy consumption in each city and county based on the city-level and county-level energy consumption structures of various industries includes: The city-level structure of energy consumption in each industry during the preset time period is weighted and smoothed to obtain the city-level structure of energy consumption in each industry. Based on the structure of each city, the energy consumption of the province is decomposed into the energy consumption of each city in the target province. Based on the industry electricity consumption growth trend, the first county-level structure of energy consumption of each industry in the preset time period is modified to obtain the county-level structure of energy consumption of each industry. Based on the structure of each district and county, the energy consumption of each city is decomposed into the corresponding districts and counties to obtain the energy consumption of each county in the target province.

[0013] The embodiments of the present invention, through a city-county structure decomposition method based on weighted moving smoothing and growth trend correction, can achieve a reasonable spatial allocation of energy consumption and improve the precision of regional energy management.

[0014] Furthermore, the preliminary forecast of energy supply for each city and county is made based on the energy supply weight, energy production, and energy import volume of each district and county. Then, the heating and electricity supply are predicted based on the standard coal consumption for heating and electricity supply, and these predictions are added to the preliminary forecast results to obtain the energy supply for each city and county, including: The data of each energy supply capacity indicator are weighted in layers to obtain multiple energy supply weights for each district and county. Based on the energy supply weights, energy production and energy imports, the supply volume is predicted to obtain the energy supply volume of each first municipal area and each first county area. Based on the unit aging rate correction, the standard coal consumption for heating and power supply are used to predict the heating and power supply respectively. The prediction results are then added to the energy supply of each first city area and each first county area to obtain the energy supply of each city area and each county area.

[0015] The embodiments of this invention, through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, can scientifically predict the energy supply of each district and county, providing accurate supply-side data support for energy dispatch; by introducing unit aging rate correction for standard coal consumption prediction of heating and power supply, it can accurately reflect equipment efficiency decline and improve the reliability of heating and power supply capacity prediction.

[0016] Furthermore, the energy supply capacity index data is hierarchically weighted to obtain multiple energy supply weights for each district and county. Based on these energy supply weights, energy production, and energy imports, supply forecasts are made to obtain the energy supply for each first municipality and each first county, including: Data on energy supply capacity indicators, energy imports, energy production, and energy production of each district and county in the target province during the preset time period are collected to determine multiple energy supply weights for each district and county, as well as the predicted values ​​of energy imports, energy production, and energy production. According to the energy supply weights mentioned above, the provincial energy transfer volume is decomposed to each city and each district and county, and then added to the corresponding energy production of each city and each county to obtain the energy supply of each second city and each second county. Based on the multiple first energy processing and conversion ratios within the preset time period, the energy supply of each second municipality and the energy supply of each second county are decomposed into energy processing and conversion amounts for each municipality, energy supply for each first municipality, energy processing and conversion amounts for each county, and energy supply for each first county.

[0017] The embodiments of the present invention can scientifically predict the energy supply of each district and county through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, providing accurate supply-side data support for energy dispatch.

[0018] Furthermore, the standard coal consumption for heating and power generation, corrected based on the unit aging rate, are used to predict the heating and power supply respectively. The prediction results are then added to the corresponding energy supply amounts for each of the first municipalities and the first counties to obtain the energy supply amounts for each municipality and each county, including: The standard coal consumption, heat supply and power supply of each unit in the target province during the preset time period are collected to calculate the first standard coal consumption for heat supply and the first standard coal consumption for power supply of each unit. The first standard coal consumption for heat supply and the first standard coal consumption for power supply are corrected according to the aging rate of each unit to obtain the standard coal consumption for heat supply and the standard coal consumption for power supply of each unit. Based on the energy processing and conversion volume of each city and each county, the energy supply of each second city and each second county, as well as the energy supply of each third city and each third county, are calculated using the standard coal consumption for heating and the standard coal consumption for power supply, respectively. The energy supply of each of the first municipalities, the energy supply of each of the second municipalities, and the energy supply of each of the third municipalities are added together to obtain the energy supply of each municipality. The energy supply of each of the first county, the energy supply of each of the second county, and the energy supply of each of the third county are added together to obtain the energy supply of each county.

[0019] The embodiments of the present invention, by introducing a standard coal consumption prediction for heating and power supply based on unit aging rate correction, can accurately reflect the decline in equipment efficiency and improve the reliability of heating and power supply capacity prediction.

[0020] Furthermore, the construction of a two-tier energy dispatch model based on the energy consumption of each city and each county, as well as the energy supply of each city and each county, includes: The energy consumption of each county is compared with the corresponding energy supply of each county to determine the first energy balance of the corresponding county, and the energy consumption of each city is compared with the corresponding energy supply of each city to determine the second energy balance of the corresponding city. A first energy dispatch model is constructed based on each of the first energy balance situations, and a second energy dispatch model is constructed based on each of the second energy balance situations. The first energy dispatch model is used as the first layer, and the second energy dispatch model is used as the second layer to construct a two-layer energy dispatch model.

[0021] This invention, through the construction of a two-tiered energy dispatch model at the county / district / city level, enables optimized dispatching by layer and region, effectively reducing energy transmission costs and improving system operating efficiency.

[0022] Another embodiment of the present invention provides a provincial energy balance optimization scheduling device, including: an energy consumption forecasting module, an energy supply forecasting module, a scheduling model construction module, and an energy scheduling module; The energy consumption forecasting module is used to forecast electricity consumption based on the electricity consumption characteristics of various industries over a preset time period, and to calculate the provincial energy consumption based on the electricity consumption forecasting results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county. The energy supply forecasting module is used to make preliminary forecasts of the energy supply of each city and each county based on the energy supply weight, energy production and energy import of each district and county. Then, it forecasts the heat supply and power supply based on the standard coal consumption for heating and the standard coal consumption for power supply and adds them to the preliminary forecast results to obtain the energy supply of each city and each county. The scheduling model construction module is used to construct a two-layer energy scheduling model based on the energy consumption of each city and the energy consumption of each county, as well as the energy supply of each city and the energy supply of each county; wherein, the two-layer energy scheduling model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints; The energy dispatch module is used to solve the two-layer energy dispatch model in layers using a solver, generate provincial energy dispatch instructions, and control the provincial energy network of the target province to perform energy dispatch according to the provincial energy dispatch instructions. Attached Figure Description

[0023] Figure 1 A flowchart illustrating one embodiment of the provincial energy balance optimization scheduling method provided by the present invention; Figure 2 This is a schematic diagram of one embodiment of the provincial energy balance optimization scheduling device provided by the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0026] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0029] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0030] See Figure 1 To address the problem of unclear default accounting for energy resources by region and category in existing technologies, an embodiment of the present invention provides a provincial energy balance optimization scheduling method, including steps S101 to S104: Step S101: Based on the electricity consumption characteristics of each industry within a preset time period, electricity consumption is predicted, and the provincial energy consumption is calculated based on the electricity consumption prediction results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county.

[0031] Preferably, the electricity consumption forecast is performed based on the electricity consumption characteristics of each industry within a preset time period, and the provincial energy consumption is calculated based on the electricity consumption forecast results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county, including: Based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. Based on the energy consumption of the first province and the energy structure of each industry, energy conversion is performed to obtain the energy consumption of the province. Based on the city and county structure of energy consumption of each industry, the energy consumption of each city and the energy consumption of each county are calculated respectively.

[0032] Preferably, based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province, including: First, collect the electricity consumption of the first industry in each sector of the target province within the preset time period.

[0033] In one embodiment, the electricity consumption of the first industry collected from various industries is: ;in, The data represents the electricity consumption of 51 industries (including 19 categories of industries and 33 major categories of manufacturing industries). Representatives collected a total of The first industry's electricity consumption in each year.

[0034] Second, feature extraction is performed on the electricity consumption of each of the first industries to obtain the industry electricity consumption characteristics of each industry; wherein, the industry electricity consumption characteristics include the industry electricity consumption compound growth rate, the industry annual fluctuation range, the industry electricity consumption contribution ratio, and the industry electricity consumption proportion trend characteristics.

[0035] In the previous embodiment, the compound annual growth rate of industry electricity consumption can be expressed as: The annual fluctuation range of the industry can be expressed as ,in, The industry's contribution to electricity consumption can be expressed as: The trend characteristics of industry electricity consumption proportion can be expressed as follows: The above four characteristics are standardized to eliminate dimensions, specifically as follows: ; in, For the industry The Original values ​​of each feature; For all industries The mean of the original values ​​of each feature. For all industries The standard deviation of the original values ​​of each feature.

[0036] Third, based on the electricity consumption characteristics of each industry, the K-Means algorithm is used for clustering to obtain multiple industry groups; wherein, the number of industry groups is determined according to the profile coefficient of each industry.

[0037] In the previous embodiment, traversal There are several situations; among them, The industry classification number represents the minimum number of industries that must be divided into at least two industry groups, with each industry group containing at least three industries, thus avoiding single-industry clusters or overly small clusters. The K-Means algorithm is used to generate clustering results for each... The clustering results are used to calculate the profile coefficients for all industries. : ; in, For the industry Average distance from other industries in the same category; For the industry The average distance to all industries within the nearest category. Calculate each Corresponding average profile coefficient ,choose The largest This represents the optimal number of categories. The final result is... Industry clusters Each group contains several industries with similar electricity consumption characteristics.

[0038] Fourth, a grey prediction model is used to predict the electricity consumption of each industry group, resulting in multiple first industry group electricity consumptions. An ARIMA model is then used to correct the residuals of each first industry group electricity consumption, resulting in multiple industry group electricity consumptions.

[0039] In the previous embodiment, for each industry group ,in A grey prediction model based on ARIMA residual correction is used to predict electricity consumption. The electricity consumption for the industry group in a preset year (in this embodiment, "preset year" refers to a year within the "preset time period") is also used. for All industries Summary of electricity consumption for the preset year A grey prediction model is used for preliminary forecasting, and the electricity consumption of the industry group in the preset years is accumulated to obtain an accumulated sequence. Construct a first-order linear differential equation And calculated using the least squares method and .based on and Predict the cumulative value Ultimately, the industry group The gray prediction result for electricity consumption is: The grey prediction results are further optimized by using the ARIMA model to correct residuals. ; in, For the preset time period Annual residuals. Based on the residual series over a pre-defined time period, the ARIMA model is used to predict the residuals. By combining the grayscale prediction results with the residual correction of ARIMA, the final comprehensive prediction results for the industry group are obtained. .

[0040] Fifth, based on the electricity consumption data of each industry group and the proportion of each industry in the corresponding industry group, the industry electricity consumption of each industry is calculated, and the electricity consumption of all industries is added together to obtain the first provincial energy consumption of the target province.

[0041] In the previous embodiment, for Each industry within Calculate its percentage within a preset time period within the group. Use this percentage and time. Perform linear regression And obtained through the least squares method and Substituting these values ​​into the formula, we obtain a preliminary forecast of the industry share. To ensure that the sum of the percentages of all industries within the group is 1 and to avoid negative percentages, the predicted percentage value is normalized to obtain the final predicted percentage value. Calculate electricity consumption for each industry based on the predicted percentage. The energy consumption of the first province is obtained by summing up the electricity consumption of various industries. .

[0042] Preferably, the step of calculating the provincial energy consumption based on the energy consumption of the first province and the energy structure of each industry to obtain the provincial energy consumption includes: First, the energy structure of each industry during the preset time period is fitted with an ARIMA model to obtain multiple first energy conversion ratios for each industry; wherein, the first energy conversion ratio corresponds to one of four energy sources: coal, oil, natural gas, and heat.

[0043] In the previous embodiment, based on the energy consumption characteristics of different industries across the province over a preset time period, structural correlations between electricity and coal, oil, natural gas, and heat energy were established for each industry: ; in, It consists of four energy sources: coal, oil, natural gas, and heat. It is the preset time period number Year The industry's electricity consumption; It is the preset time period number Year The industry's consumption of coal, oil, natural gas, and heat energy; It is the preset time period number Year The industry's energy conversion ratio. An ARIMA model is used to fit the trend of the energy conversion ratio over a preset time period to obtain the first energy conversion ratio. .

[0044] Second, based on the amount of electricity substitution during the preset time period, the conversion ratio of each of the first energy sources is adjusted to obtain multiple energy conversion ratios for each of the industries.

[0045] In the previous embodiment, based on the electricity substitution growth intensity coefficient of different industries... right Make corrections to obtain the adjusted energy conversion ratio. .

[0046] Third, energy consumption is calculated based on the energy consumption of the first province and the energy conversion ratios of each province to obtain the energy consumption of multiple second provinces. The energy consumption of the first province is then added to the energy consumption of each of the second provinces to obtain the energy consumption of the target province.

[0047] In the previous embodiment, the energy consumption of the first province was converted according to the energy conversion ratio, and the energy consumption of different industries and products was converted accordingly: ; Where 1.229 is the standard coal conversion factor for electricity (1 kWh of electricity = 0.1229 kg of standard coal, multiplied by 10 here to unify the unit to "tons of standard coal / 10,000 kWh"); yes Provincial energy consumption of the industry; for industry The second-largest provincial energy consumption; for The province with the highest energy consumption in the industry.

[0048] Preferably, the calculation of energy consumption in each city and county based on the city-level and county-level energy consumption structures of various industries includes: First, a weighted moving smoothing method is applied to the first city structure of energy consumption in each industry during the preset time period to obtain the city structure of energy consumption in each industry.

[0049] In the previous embodiment, the first city structure of energy consumption for each industry during the preset time period is as follows: Using a weighted moving average smoothing method, the proportion of different cities in the province by industry and energy type was obtained, i.e., the city structure: ; in, The length of the moving window; For the first The weight of the period satisfies To ensure that the most recent data has the greatest impact; for The first phase of the city structure. For the smoothed... After normalization adjustment, the adjusted result is obtained. : ; in, For each prefecture-level city in the target province; For different industries; The five energy sources are coal, oil, natural gas, electricity, and heat. The city-level structure of energy consumption across various industries; This refers to the provincial energy consumption by industry and energy type.

[0050] Second, based on the structure of each city, the energy consumption of the province is decomposed into the energy consumption of each city in the target province.

[0051] In the previous embodiment, based on the normalized... The energy consumption of a province is broken down into its cities and prefectures to obtain the energy consumption of each city in the target province: ; in, This refers to the city's energy consumption by industry and energy type.

[0052] Third, based on the industry electricity consumption growth trend, the first county-level structure of energy consumption in each industry during the preset time period is modified to obtain the county-level structure of energy consumption in each industry.

[0053] In the previous embodiment, the first county-level structure of energy consumption for each industry in a preset year is as follows: The first county-level structure of energy consumption in various industries during the preset time period is as follows: Introducing an industry-specific electricity consumption growth trend adjustment coefficient. ,right Make corrections: ; ; ; ; in, For prefecture-level cities Inner Districts and Counties of The industry's average annual electricity consumption growth rate; For prefecture-level cities of The industry's average annual electricity consumption growth rate. This indicates that electricity consumption in districts and counties is growing faster than the average level in prefecture-level cities, and the ratio should be revised more quickly. This indicates that electricity consumption in districts and counties is lagging behind the average level of prefecture-level cities, and the ratio should be revised accordingly. After normalization adjustment, the adjusted result is obtained. .

[0054] Fourth, based on the structure of each district and county, the energy consumption of each city is decomposed to each district and county to obtain the energy consumption of each county in the target province.

[0055] In the previous embodiment, based on the normalized... The energy consumption of each city is then broken down to the corresponding districts and counties to obtain the energy consumption of each county in the target province: ; in, For prefecture-level cities The corresponding county-level energy consumption by industry and energy type.

[0056] Step S102: Based on the energy supply weight, energy production and energy import of each district and county, make a preliminary forecast of the energy supply of each city and each county. Then, based on the standard coal consumption for heating and standard coal consumption for power supply, forecast the heat supply and power supply and add them to the preliminary forecast results to obtain the energy supply of each city and each county.

[0057] Preferably, the preliminary forecast of energy supply for each city and each county is made based on the energy supply weight, energy production, and energy import volume of each district and county. Then, the heating and electricity supply are predicted based on the standard coal consumption for heating and electricity supply, and these predictions are added to the preliminary forecast results to obtain the energy supply for each city and each county. This includes: The data of each energy supply capacity indicator are weighted in layers to obtain multiple energy supply weights for each district and county. Based on the energy supply weights, energy production and energy imports, the supply volume is predicted to obtain the energy supply volume of each first municipal area and each first county area. Based on the unit aging rate correction, the standard coal consumption for heating and power supply are used to predict the heating and power supply respectively. The prediction results are then added to the energy supply of each first city area and each first county area to obtain the energy supply of each city area and each county area.

[0058] Preferably, the step of performing hierarchical weighting on the energy supply capacity index data to obtain multiple energy supply weights for each district and county, and forecasting the supply based on each energy supply weight, each energy production volume, and each energy import volume to obtain the energy supply for each first municipality and each first county, includes: First, data on energy supply capacity indicators, energy imports to the first province, energy production to the first city, and energy production to the first county are collected for each district and county in the target province during the preset time period. This is to determine multiple energy supply weights for each district and county, as well as the predicted values ​​for energy imports to the province, energy production to the city, and energy production to the county. The energy supply weights correspond to one of three energy sources: coal, oil, and natural gas.

[0059] In the previous embodiment, an "energy supply capacity index" system was constructed from several dimensions, including related facility capacity, industrial production, and people's consumption, and multiple energy supply weights for each district and county were calculated. The province's energy imports will be allocated to districts and counties. For details on coal energy supply capacity indicators, oil energy supply capacity indicators, and natural gas energy supply capacity indicators, please refer to Tables 1, 2, and 3.

[0060] Table 1 - Coal Supply Capacity Indicators Table 2 - Petroleum Supply Capacity Indicators Table 3 - Natural Gas Supply Capacity Indicators A linear combination model is used to perform hierarchical weighting of the energy supply capacity index data: a normalization method is used to perform a linear transformation on the secondary index data to eliminate dimensions, and the normalized data is then weighted accordingly. The first indicator Let the time series data be denoted as First calculate the... The first indicator The proportion of each time series value to the total value of the indicator Next, the entropy value of the secondary indicator is calculated. ,in Then calculate the first... Information redundancy of the indicator Finally, the weights corresponding to each secondary indicator data are obtained. A primary index is the weighted sum of its subordinate secondary indices, i.e. Repeat the above steps to calculate the weights of the primary indicators for each district and county, and then calculate the weighted average supply capacity index for each product category for each district and county. = ; in, The overall index of energy supply capacity of districts and counties; For the first One primary indicator; For the first The weights corresponding to each primary indicator. The energy supply weights for each district and county. For index percentage: ; in, for District and County The overall index of energy supply capacity.

[0061] In the previous embodiment, the energy production of each first county in the target province in a preset year was collected as follows: Construct a linear trend model And calculated using the least squares method and ,in , The energy production of each county in the target province was obtained by trend extrapolation using a linear trend model. Similarly, the provincial energy import volume and the energy production of each city in the target province can be calculated, where the provincial energy import volume is... Total energy imports into the province Subtract the total energy transferred out of the province .

[0062] Second, based on the energy supply weights of each region, the energy transfer volume of the province is decomposed to each city and each county, and then added to the corresponding energy production of each city and each county to obtain the energy supply of each second city and each second county.

[0063] In the previous embodiment, based on the energy supply weights, the provincial energy import volume is decomposed to each district and county to obtain the energy import volume of each county in the target province. Then, the energy import volume of each county is added to the corresponding energy production of each county to obtain the energy supply of each second county in the target province. ; in, The second county-level energy supply, categorized by energy type; for District and County The amount of energy transferred into counties for this type of energy; for District and County The county-level energy production of each type of energy is calculated. Similarly, the energy supply of each second-tier city in the target province can be obtained. The energy supply of the target province by energy type in the second-tier cities is the sum of the energy supplies of each second-tier county. .

[0064] Third, based on the multiple first energy processing and conversion ratios of the preset time period, the energy supply of each second municipality and the energy supply of each second county are decomposed into the energy processing and conversion of each municipality and the energy supply of each first municipality, as well as the energy processing and conversion of each county and the energy supply of each first county.

[0065] In the previous embodiment, a portion of the supply of coal, oil, and natural gas is used for processing and conversion processes such as power generation and heating, while another portion is directly used for end-user consumption. The processing and conversion ratios of multiple primary energy sources for the target province in a preset year are obtained. Then, a weighted moving average smoothing method is applied to obtain multiple energy processing and conversion ratios for the target province. : ; in, The length of the moving window; For the first The weight of the period satisfies To ensure that the most recent data has the greatest impact. for The first energy processing and conversion ratio of the period. Based on the energy processing and conversion ratios of each period. Calculate the provincial energy processing and conversion volume in the second provincial energy supply by energy type. The installation schedule for each district and county will be determined based on the installation plan. Then, based on the proportion of different generating units (coal-fired, oil-fired, and gas-fired) in each district / county to the total number of generating units (coal-fired, oil-fired, and gas-fired) in the province, the energy processing and conversion volume of the province is allocated to the districts / counties, resulting in the energy processing and conversion volume of each county and the energy supply volume of each primary county: ; ; in, These refer to the equipment capacities of coal-fired, oil-fired, and gas-fired units, respectively. This represents the sum of the heating capacity of all thermal power units (coal-fired, oil-fired, and gas-fired) in the province. Similarly, the energy processing and conversion volume of each city in the target province and the energy supply volume of each primary city can be calculated.

[0066] Preferably, the standard coal consumption for heating and the standard coal consumption for power generation, corrected based on the unit aging rate, are used to predict the heating and power consumption, respectively. The prediction results are then added to the corresponding energy supply amounts for each of the first municipalities and the first counties to obtain the energy supply amounts for each municipality and each county, including: First, the standard coal consumption, heating capacity, and power supply of each unit in the target province during the preset time period are collected to calculate the first standard coal consumption for heating and the first standard coal consumption for power supply of each unit. The first standard coal consumption for heating and the first standard coal consumption for power supply are then corrected according to the aging rate of each unit to obtain the standard coal consumption for heating and the standard coal consumption for power supply of each unit.

[0067] In the previous embodiment, the standard coal equivalent, heat supply, and power supply for the preset year were collected as follows: , and The first standard coal consumption for heating of each unit was calculated based on the standard coal consumption and the heat supply. The first standard coal consumption for power supply of each unit is calculated based on the standard coal consumption and power supply. .

[0068] In the previous embodiment, the average standard coal consumption for heating over a preset time period was calculated. The aging rate of each unit was calculated based on the amount of standard coal produced. The average standard coal consumption of each primary heating unit was corrected according to the aging rate of each unit, and the corresponding standard coal consumption of each unit was obtained. Calculate the average coal consumption of the first power supply standard over a preset time period. The average standard coal consumption for power supply of each unit was corrected according to the aging rate of each unit, and the corresponding standard coal consumption for power supply of each unit was obtained. .

[0069] Second, based on the energy processing and conversion volume of each city and each county, the energy supply of each second city and each second county, as well as the energy supply of each third city and each third county, are calculated using the standard coal consumption for heating and the standard coal consumption for power supply.

[0070] In the previous embodiment, the comprehensive standard coal consumption for heating in each district and county was calculated based on the standard coal consumption for heating of each unit: ; in, They are respectively Comprehensive standard coal consumption for heating in districts and counties using coal-fired, oil-fired, and gas-fired power units; for Type of unit The installed capacity; for All within the district / county Total installed capacity of unit type. Based on the energy processing and conversion volume of each county and the standard coal consumption for comprehensive heating, corresponding calculations are performed to obtain the energy supply of each second county in the target province. Similarly, the energy supply of each second municipality in the target province can be calculated.

[0071] In the previous embodiment, the comprehensive standard coal consumption for power supply in each district and county was calculated based on the standard coal consumption for power supply of each unit: ; in, They are respectively The comprehensive standard coal consumption for power generation by coal-fired, oil-fired, and gas-fired power units in districts and counties; for Type of unit The installed capacity; for All within the district / county Total installed capacity of unit type. Based on the energy processing and conversion volume of each county and the standard coal consumption for comprehensive power supply, corresponding calculations are performed to obtain the thermal power generation of each county in the target province. The energy supply of the third county includes primary electricity generation. Thermal power generation and incoming power The three parts refer to the primary power supply, including hydropower, nuclear power, solar power, and wind power, and the installed capacity of different districts and counties is predicted based on the installed capacity planning. The corresponding primary power generation is calculated by combining the average utilization hours of the district / county with the predicted installed capacity: ; in, The primary power generation of the district / county; They are respectively The installed capacity of hydropower, nuclear power, solar power, and wind power in districts and counties; They are respectively Average utilization hours of hydropower, nuclear power, solar power, and wind power in districts and counties. Imported electricity. The calculations are primarily based on the situation of various external power transmission channels within the province. Assuming that external power is preferentially consumed locally before being transmitted to other parts of the province, the power supply capacity of the region can be calculated based on the port number of the external power transmission channel. The energy supply capacity of each third-level county is obtained by adding up the primary power generation, thermal power generation, and external power generation of each county. Similarly, the energy supply of each third municipality in the target province can be calculated.

[0072] Third, the energy supply of each of the first municipalities, the energy supply of each of the second municipalities, and the energy supply of each of the third municipalities are added together to obtain the energy supply of each municipality. The energy supply of each of the first counties, the energy supply of each of the second counties, and the energy supply of each of the third counties are added together to obtain the energy supply of each county.

[0073] Step S103: Construct a two-tier energy dispatch model based on the energy consumption of each city and county, as well as the energy supply of each city and county; wherein the two-tier energy dispatch model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints.

[0074] Preferably, the step of constructing a two-tier energy dispatch model based on the energy consumption of each of the aforementioned municipalities and counties, as well as the energy supply of each of the aforementioned municipalities and counties, includes: First, the energy consumption of each county is compared with the corresponding energy supply of each county to determine the first energy balance of the corresponding county, and the energy consumption of each city is compared with the corresponding energy supply of each city to determine the second energy balance of the corresponding city.

[0075] In the previous embodiment, the energy consumption of each county was compared with the corresponding energy supply to determine the first energy balance of the corresponding district / county: ; in, It includes five energy sources: coal, oil, natural gas, electricity, and heat. for districts and counties The primary energy balance of energy types; for districts and counties County-level energy supply for various energy types; for districts and counties County-level energy consumption for each type of energy source. The overall primary energy balance can be categorized into three states: one where county-level energy supply exceeds county-level energy consumption, resulting in a surplus for that county. When a county's energy supply equals its energy consumption, the county is in balance; when a county's energy supply is less than its energy consumption, the county is in deficit. Similarly, the second energy balance situation in each city can be obtained.

[0076] Second, a first energy dispatch model is constructed based on each of the first energy balance situations, and a second energy dispatch model is constructed based on each of the second energy balance situations. The first energy dispatch model is used as the first layer, and the second energy dispatch model is used as the second layer to construct a two-layer energy dispatch model.

[0077] In the previous embodiment, the two-tier energy dispatch model aims to minimize the total amount of flowing energy. ; in, In the hierarchy (1 = district / county, 2 = prefecture / city) From Regional delivery to The region's energy consumption; From Regional delivery to The transmission distance between regions. The two-tier energy dispatch model is constrained by supply constraints (the amount of energy sent out by each region is less than or equal to the local surplus, and the amount of energy received by each region is less than or equal to the local deficit) and channel capacity constraints (the energy transmission capacity between two regions is less than the channel capacity between the two regions). ; in, hierarchical middle The amount of energy transmitted from the region; hierarchical middle The region's local surplus.

[0078] ; in, hierarchical middle The amount of energy received by the region; hierarchical middle Local vacancies in the region.

[0079] ; in, for Region and Inter-regional channel capacity. When the provincial energy supply is greater than or equal to the provincial energy consumption, the transmission value equals the province's total energy surplus; when the provincial energy supply is less than or equal to the provincial energy consumption, the transmission value equals the province's total deficit.

[0080] Step S104: The two-layer energy dispatch model is solved hierarchically using a solver to generate provincial energy dispatch instructions, and the provincial energy network of the target province is controlled to perform energy dispatch according to the provincial energy dispatch instructions.

[0081] In the previous embodiment, the solution to the two-tier energy dispatch model is based on the following hierarchical energy flow rules: energy flow between districts and counties within a prefecture-level city, and energy flow between cities within a province. Unbalanced deficits at each level are automatically transferred to the next level (i.e., deficits at the district / county level are transferred to the prefecture-level city level). When a certain area (level) is within a certain range... At that time, the region was a district or county; the level was... When the energy in a region (prefecture-level city) reaches a balance (i.e., the difference is 0), the energy flow in that region terminates; when there are no longer areas with energy surplus and areas with energy deficit within a certain level (prefecture-level city or district / county), the energy flow at that level terminates.

[0082] This invention, through industry clustering based on electricity consumption characteristics and a combined prediction model employing grey prediction and ARIMA residual correction, effectively improves the accuracy of electricity consumption prediction for various industries, providing a reliable data foundation for subsequent energy balance calculations. By using an energy conversion method combining trend fitting and electricity substitution correction, it accurately predicts the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand prediction. Through a district / county structure decomposition method using weighted moving smoothing and growth trend correction, it achieves a reasonable spatial allocation of energy consumption, improving the precision of regional energy management. Through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, it scientifically predicts the energy supply of each district / county, providing accurate supply-side data support for energy dispatch. By introducing unit aging rate correction for standard coal consumption prediction in heating and power generation, it accurately reflects equipment efficiency degradation, improving the reliability of heating and power supply capacity prediction. By constructing a district / county-city two-tier energy dispatch model, it achieves hierarchical and regional optimized dispatch, effectively reducing energy transmission costs and improving system operating efficiency.

[0083] Optionally, in this embodiment of the invention, the process of predicting electricity consumption based on the electricity consumption characteristics of various industries over a preset time period, calculating the provincial energy consumption based on the electricity consumption prediction results and the energy structure of each industry, and then decomposing the provincial energy consumption into the energy consumption of each city and each county based on the city and county structure of energy consumption in each industry, includes: Based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. Based on the energy consumption of the first province and the energy structure of each industry, energy conversion is performed to obtain the energy consumption of the province. Based on the city and county structure of energy consumption of each industry, the energy consumption of each city and the energy consumption of each county are calculated respectively.

[0084] This invention, through industry clustering based on electricity consumption characteristics and a combined prediction model employing grey prediction and ARIMA residual correction, effectively improves the accuracy of electricity consumption prediction for various industries, providing a reliable data foundation for subsequent energy balance calculations. By using an energy conversion method combining trend fitting and electricity substitution correction, it accurately predicts the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand forecasting. Furthermore, through a city / district / county structure decomposition method using weighted moving smoothing and growth trend correction, it achieves a reasonable spatial allocation of energy consumption, improving the precision of regional energy management.

[0085] Optionally, in this embodiment of the invention, the process of clustering industries in a target province into multiple industry groups based on the electricity consumption characteristics of various industries over a preset time period, and using a grey prediction model based on ARIMA residual correction to predict the electricity consumption of each industry group to obtain the energy consumption of the first province, includes: Collect the electricity consumption of the first industry in each industry of the target province within the preset time period; Features are extracted from the electricity consumption of each of the first industries to obtain the industry electricity consumption characteristics of each industry; wherein, the industry electricity consumption characteristics include the industry electricity consumption compound growth rate, the industry annual fluctuation range, the industry electricity consumption contribution ratio, and the industry electricity consumption proportion trend characteristics. Based on the electricity consumption characteristics of each industry, the K-Means algorithm is used for clustering to obtain multiple industry groups; wherein, the number of industry groups is determined according to the profile coefficient of each industry. The grey prediction model is used to predict the electricity consumption of each industry group, and the corresponding electricity consumption of multiple first industry groups is obtained. The ARIMA model is used to correct the residuals of the electricity consumption of each first industry group, and the corresponding electricity consumption of multiple industry groups is obtained. Based on the electricity consumption data of each industry group and the proportion of each industry in the corresponding industry group, the industry electricity consumption of each industry is calculated, and the electricity consumption of all industries is added together to obtain the first provincial energy consumption of the target province.

[0086] The embodiments of the present invention can effectively improve the accuracy of electricity consumption prediction by using a combined prediction model of gray prediction and ARIMA residual correction through industry clustering based on electricity consumption characteristics, and provide a reliable data foundation for subsequent energy balance calculations.

[0087] Optionally, in this embodiment of the invention, the step of calculating the provincial energy consumption based on the energy consumption of the first province and the energy structure of each industry to obtain the provincial energy consumption includes: The ARIMA model is used to fit the trend of the energy structure of each industry during the preset time period to obtain multiple first energy conversion ratios for each industry; wherein, the first energy conversion ratio corresponds to one of four energy sources: coal, oil, natural gas and heat. Based on the amount of electricity substitution during the preset time period, the conversion ratio of each of the first energy sources is adjusted to obtain multiple energy conversion ratios for each of the industries. Energy consumption is calculated based on the energy consumption of the first province and the energy conversion ratios of each province to obtain the energy consumption of multiple second provinces. The energy consumption of the first province is then added to the energy consumption of each of the second provinces to obtain the energy consumption of the target province.

[0088] The embodiments of the present invention employ an energy conversion method that combines trend fitting with electricity substitution correction, which can accurately predict the consumption structure of multiple energy sources and enhance the comprehensiveness and foresight of energy demand forecasting.

[0089] Optionally, in this embodiment of the invention, the calculation of energy consumption in each city and each county based on the city-level and county-level energy consumption structures of various industries includes: The city-level structure of energy consumption in each industry during the preset time period is weighted and smoothed to obtain the city-level structure of energy consumption in each industry. Based on the structure of each city, the energy consumption of the province is decomposed into the energy consumption of each city in the target province. Based on the industry electricity consumption growth trend, the first county-level structure of energy consumption of each industry in the preset time period is modified to obtain the county-level structure of energy consumption of each industry. Based on the structure of each district and county, the energy consumption of each city is decomposed into the corresponding districts and counties to obtain the energy consumption of each county in the target province.

[0090] The embodiments of the present invention, through a city-county structure decomposition method based on weighted moving smoothing and growth trend correction, can achieve a reasonable spatial allocation of energy consumption and improve the precision of regional energy management.

[0091] Optionally, in this embodiment of the invention, the preliminary prediction of energy supply for each city and each county based on the energy supply weight, energy production, and energy import volume of each district and county, followed by the prediction of heating and power supply based on standard coal consumption for heating and standard coal consumption for power supply, and the addition of these predictions to the preliminary prediction results to obtain the energy supply for each city and each county, includes: The data of each energy supply capacity indicator are weighted in layers to obtain multiple energy supply weights for each district and county. Based on the energy supply weights, energy production and energy imports, the supply volume is predicted to obtain the energy supply volume of each first municipal area and each first county area. Based on the unit aging rate correction, the standard coal consumption for heating and power supply are used to predict the heating and power supply respectively. The prediction results are then added to the energy supply of each first city area and each first county area to obtain the energy supply of each city area and each county area.

[0092] The embodiments of this invention, through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, can scientifically predict the energy supply of each district and county, providing accurate supply-side data support for energy dispatch; by introducing unit aging rate correction for standard coal consumption prediction of heating and power supply, it can accurately reflect equipment efficiency decline and improve the reliability of heating and power supply capacity prediction.

[0093] Optionally, in this embodiment of the invention, the step of performing hierarchical weighting on the energy supply capacity index data to obtain multiple energy supply weights for each district and county, and forecasting the supply based on each energy supply weight, each energy production volume, and each energy import volume to obtain the energy supply for each first municipality and each first county, includes: Data on energy supply capacity indicators, energy imports, energy production, and energy production of each district and county in the target province during the preset time period are collected to determine multiple energy supply weights for each district and county, as well as the predicted values ​​of energy imports, energy production, and energy production. According to the energy supply weights mentioned above, the provincial energy transfer volume is decomposed to each city and each district and county, and then added to the corresponding energy production of each city and each county to obtain the energy supply of each second city and each second county. Based on the multiple first energy processing and conversion ratios within the preset time period, the energy supply of each second municipality and the energy supply of each second county are decomposed into energy processing and conversion amounts for each municipality, energy supply for each first municipality, energy processing and conversion amounts for each county, and energy supply for each first county.

[0094] The embodiments of the present invention can scientifically predict the energy supply of each district and county through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, providing accurate supply-side data support for energy dispatch.

[0095] Optionally, in this embodiment of the invention, the standard coal consumption for heating and the standard coal consumption for power generation, corrected based on the unit aging rate, are used to predict the heating and power supply respectively, and the prediction results are added to the corresponding energy supply of each of the first municipalities and the energy supply of each of the first counties to obtain the energy supply of each municipality and the energy supply of each county, including: The standard coal consumption, heat supply and power supply of each unit in the target province during the preset time period are collected to calculate the first standard coal consumption for heat supply and the first standard coal consumption for power supply of each unit. The first standard coal consumption for heat supply and the first standard coal consumption for power supply are corrected according to the aging rate of each unit to obtain the standard coal consumption for heat supply and the standard coal consumption for power supply of each unit. Based on the energy processing and conversion volume of each city and each county, the energy supply of each second city and each second county, as well as the energy supply of each third city and each third county, are calculated using the standard coal consumption for heating and the standard coal consumption for power supply, respectively. The energy supply of each of the first municipalities, the energy supply of each of the second municipalities, and the energy supply of each of the third municipalities are added together to obtain the energy supply of each municipality. The energy supply of each of the first county, the energy supply of each of the second county, and the energy supply of each of the third county are added together to obtain the energy supply of each county.

[0096] The embodiments of the present invention, by introducing a standard coal consumption prediction for heating and power supply based on unit aging rate correction, can accurately reflect the decline in equipment efficiency and improve the reliability of heating and power supply capacity prediction.

[0097] Optionally, in this embodiment of the invention, the step of constructing a two-tier energy dispatch model based on the energy consumption of each city and each county, as well as the energy supply of each city and each county, includes: The energy consumption of each county is compared with the corresponding energy supply of each county to determine the first energy balance of the corresponding county, and the energy consumption of each city is compared with the corresponding energy supply of each city to determine the second energy balance of the corresponding city. A first energy dispatch model is constructed based on each of the first energy balance situations, and a second energy dispatch model is constructed based on each of the second energy balance situations. The first energy dispatch model is used as the first layer, and the second energy dispatch model is used as the second layer to construct a two-layer energy dispatch model.

[0098] This invention, through the construction of a two-tiered energy dispatch model at the county / district / city level, enables optimized dispatching by layer and region, effectively reducing energy transmission costs and improving system operating efficiency.

[0099] like Figure 2As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; An embodiment of the present invention provides a provincial energy balance optimization scheduling device, including: an energy consumption prediction module 201, an energy supply prediction module 202, a scheduling model construction module 203, and an energy scheduling module 204; The energy consumption prediction module 201 is used to predict electricity consumption based on the electricity consumption characteristics of each industry within a preset time period, and to calculate the provincial energy consumption based on the electricity consumption prediction results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county. The energy supply forecasting module 202 is used to make a preliminary forecast of the energy supply of each city and each county based on the energy supply weight, energy production and energy import of each district and county. Then, it forecasts the heat supply and power supply based on the standard coal consumption for heating and the standard coal consumption for power supply and adds them to the preliminary forecast results to obtain the energy supply of each city and each county. The scheduling model construction module 203 is used to construct a two-layer energy scheduling model based on the energy consumption of each city and the energy consumption of each county, as well as the energy supply of each city and the energy supply of each county; wherein, the two-layer energy scheduling model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints. The energy dispatch module 204 is used to solve the two-layer energy dispatch model in layers using a solver, generate provincial energy dispatch instructions, and control the provincial energy network of the target province to perform energy dispatch according to the provincial energy dispatch instructions.

[0100] Optionally, in this embodiment of the invention, the energy consumption forecasting module 201 includes: a first energy consumption forecasting submodule and a second energy consumption forecasting submodule; The first energy consumption prediction submodule is used to cluster the industries in the target province into multiple industry groups based on the electricity consumption characteristics of each industry over a preset time period, and use a grey prediction model based on ARIMA residual correction to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. The second energy consumption forecasting submodule is used to perform energy conversion based on the energy consumption of the first province and the energy structure of each industry to obtain the energy consumption of the province, and to calculate the energy consumption of each city and each county based on the city and county structure of energy consumption of each industry.

[0101] This invention, through industry clustering based on electricity consumption characteristics and a combined prediction model employing grey prediction and ARIMA residual correction, effectively improves the accuracy of electricity consumption prediction for various industries, providing a reliable data foundation for subsequent energy balance calculations. By using an energy conversion method combining trend fitting and electricity substitution correction, it accurately predicts the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand forecasting. Furthermore, through a city / district / county structure decomposition method using weighted moving smoothing and growth trend correction, it achieves a reasonable spatial allocation of energy consumption, improving the precision of regional energy management.

[0102] Optionally, in this embodiment of the invention, the first energy consumption prediction submodule includes: an electricity consumption acquisition unit, a feature extraction unit, a clustering and partitioning unit, an electricity consumption prediction unit, and a first provincial energy consumption unit; The electricity consumption collection unit is used to collect the electricity consumption of the first industry in each industry of the target province within the preset time period; The feature extraction unit is used to extract features from the electricity consumption of each of the first industries to obtain the industry electricity consumption features of each industry; wherein, the industry electricity consumption features include the industry electricity consumption compound growth rate, the industry annual fluctuation range, the industry electricity consumption contribution ratio, and the industry electricity consumption proportion trend features. The clustering unit is used to perform clustering based on the electricity consumption characteristics of each industry using the K-Means algorithm to obtain multiple industry groups; wherein, the number of industry groups is determined according to the profile coefficient of each industry. The electricity consumption prediction unit is used to predict the electricity consumption of each industry group using a grey prediction model, thereby obtaining the electricity consumption of multiple first industry groups, and to perform residual correction on the electricity consumption of each first industry group using an ARIMA model, thereby obtaining the electricity consumption of multiple industry groups. The first provincial energy consumption unit is used to calculate the industry electricity consumption of each industry based on the electricity consumption data of each industry group and the proportion of each industry in the corresponding industry group, and to add up the electricity consumption of all industries to obtain the first provincial energy consumption of the target province.

[0103] The embodiments of the present invention can effectively improve the accuracy of electricity consumption prediction by using a combined prediction model of gray prediction and ARIMA residual correction through industry clustering based on electricity consumption characteristics, and provide a reliable data foundation for subsequent energy balance calculations.

[0104] Optionally, in this embodiment of the invention, the second energy consumption prediction submodule includes: an energy structure unit, an energy conversion unit, and a second provincial energy consumption unit; The energy structure unit is used to perform trend fitting of the energy structure of each industry in the preset time period using an ARIMA model to obtain multiple first energy conversion ratios for each industry; wherein, the first energy conversion ratio corresponds to one of four energy sources: coal, oil, natural gas, and thermal energy. The energy conversion unit is used to correct each of the first energy conversion ratios based on the amount of electricity substitution during the preset time period, thereby obtaining multiple energy conversion ratios for each of the industries. The second provincial energy consumption unit is used to perform energy conversion based on the first provincial energy consumption and each of the energy conversion ratios to obtain multiple second provincial energy consumptions, and to add the first provincial energy consumption to each of the second provincial energy consumptions to obtain the provincial energy consumption of the target province.

[0105] The embodiments of the present invention employ an energy conversion method that combines trend fitting with electricity substitution correction, which can accurately predict the consumption structure of multiple energy sources and enhance the comprehensiveness and foresight of energy demand forecasting.

[0106] Optionally, in this embodiment of the invention, the second energy consumption forecasting submodule further includes: a prefecture-level structural unit, a city-wide energy consumption unit, a district-level structural unit, and a county-level energy consumption unit; The city structure unit is used to perform weighted shift smoothing on the first city structure of energy consumption in each industry during the preset time period to obtain the city structure of energy consumption in each industry. The municipal energy consumption unit is used to decompose the provincial energy consumption to each city based on the structure of each city, so as to obtain the municipal energy consumption of the target province. The district / county structure unit is used to modify the first district / county structure of energy consumption of each industry in the preset time period based on the industry electricity consumption growth trend, so as to obtain the district / county structure of energy consumption of each industry. The county-level energy consumption unit is used to decompose the energy consumption of each city to each district and county based on the structure of each district and county, so as to obtain the energy consumption of each county in the target province.

[0107] The embodiments of the present invention, through a city-county structure decomposition method based on weighted moving smoothing and growth trend correction, can achieve a reasonable spatial allocation of energy consumption and improve the precision of regional energy management.

[0108] Optionally, in this embodiment of the invention, the energy supply forecasting module 202 includes: a first energy supply forecasting submodule and a second energy supply forecasting submodule; The first energy supply forecasting submodule is used to perform hierarchical weighting on the data of each energy supply capacity indicator to obtain multiple energy supply weights for each district and county, and to forecast the supply based on each energy supply weight, each energy production and each energy import, so as to obtain the energy supply of each first city area and the energy supply of each first county area. The second energy supply forecasting submodule is used to forecast the heat supply and power supply based on the standard coal consumption for heating and power supply corrected for the unit aging rate, and to add the forecast results to the energy supply of each of the first municipalities and the energy supply of each of the first counties to obtain the energy supply of each municipality and the energy supply of each county.

[0109] The embodiments of this invention, through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, can scientifically predict the energy supply of each district and county, providing accurate supply-side data support for energy dispatch; by introducing unit aging rate correction for standard coal consumption prediction of heating and power supply, it can accurately reflect equipment efficiency decline and improve the reliability of heating and power supply capacity prediction.

[0110] Optionally, in this embodiment of the invention, the first energy supply forecasting submodule includes: a first energy supply forecasting unit, a second energy supply forecasting unit, and a third energy supply forecasting unit; The first energy supply forecasting unit is used to collect data on energy supply capacity indicators, energy imports, energy production, and energy production of each district and county in the target province during the preset time period, so as to determine multiple energy supply weights for each district and county, as well as the forecast values ​​of energy imports, energy production, and energy production. The second energy supply forecasting unit is used to decompose the provincial energy transfer volume to each city and county according to each energy supply weight, and add it with the corresponding energy production of each city and energy production of each county to obtain the energy supply of each second city and the energy supply of each second county. The third energy supply forecasting unit is used to decompose the energy supply of each second municipality and the energy supply of each second county into energy processing and conversion amounts of each municipality and energy supply of each first municipality, as well as energy processing and conversion amounts of each county and energy supply of each first county, according to multiple first energy processing and conversion ratios for the preset time period.

[0111] The embodiments of the present invention can scientifically predict the energy supply of each district and county through hierarchical weighted energy supply capacity assessment and processing conversion ratio analysis, providing accurate supply-side data support for energy dispatch.

[0112] Optionally, in this embodiment of the invention, the second energy supply forecasting submodule includes: a fourth energy supply forecasting unit, a fifth energy supply forecasting unit, and a sixth energy supply forecasting unit; The fourth energy supply forecasting unit is used to collect the standard coal consumption, heating and power consumption of each unit in the target province during the preset time period, so as to calculate the first heating standard coal consumption and the first power standard coal consumption of each unit, and correct the first heating standard coal consumption and the first power standard coal consumption according to the aging rate of each unit to obtain the heating standard coal consumption and power standard coal consumption of each unit. The fifth energy supply forecasting unit is used to calculate, based on the energy processing and conversion volume of each city and each county, the standard coal consumption for heating and the standard coal consumption for power supply, respectively, to obtain the energy supply volume of each second city, the energy supply volume of each second county, the energy supply volume of each third city, and the energy supply volume of each third county. The sixth energy supply forecasting unit is used to add the energy supply of each of the first municipalities, the energy supply of each of the second municipalities, and the energy supply of each of the third municipalities to obtain the energy supply of each municipality, and to add the energy supply of each of the first counties, the energy supply of each of the second counties, and the energy supply of each of the third counties to obtain the energy supply of each county.

[0113] The embodiments of the present invention, by introducing a standard coal consumption prediction for heating and power supply based on unit aging rate correction, can accurately reflect the decline in equipment efficiency and improve the reliability of heating and power supply capacity prediction.

[0114] Optionally, in this embodiment of the invention, the scheduling model construction module 203 includes: an energy balance situation submodule and a two-layer energy scheduling model submodule; The energy balance status submodule is used to compare the energy consumption of each county with the corresponding energy supply of each county to determine the first energy balance status of the corresponding county, and to compare the energy consumption of each city with the corresponding energy supply of each city to determine the second energy balance status of the corresponding city. The dual-layer energy dispatch model submodule is used to construct a first energy dispatch model based on each of the first energy balance situations, construct a second energy dispatch model based on each of the second energy balance situations, and construct a dual-layer energy dispatch model by using the first energy dispatch model as the first layer and the second energy dispatch model as the second layer.

[0115] This invention, through the construction of a two-tiered energy dispatch model at the county / district / city level, enables optimized dispatching by layer and region, effectively reducing energy transmission costs and improving system operating efficiency.

[0116] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the provincial energy balance optimization scheduling method provided by any of the above-described method embodiments of the present invention.

[0117] This invention, through its energy consumption forecasting module 201, performs industry clustering based on electricity consumption characteristics and employs a combined forecasting model of grey prediction and ARIMA residual correction. This effectively improves the accuracy of electricity consumption forecasting for various industries, providing a reliable data foundation for subsequent energy balance calculations. Furthermore, by using an energy conversion method combining trend fitting and electricity substitution correction, the energy consumption forecasting module 201 can accurately predict the consumption structure of multiple energy sources, enhancing the comprehensiveness and foresight of energy demand forecasting. Finally, through its weighted moving smoothing and growth trend correction-based decomposition method for city, district, and county structures, the energy consumption forecasting module 201 can achieve a reasonable spatial allocation of energy consumption, improving regional efficiency. The system improves the sophistication of energy management. Through the layered weighted energy supply capacity assessment and processing conversion ratio analysis of the energy supply forecast module 202, it can scientifically predict the energy supply of each district and county, providing accurate supply-side data support for energy dispatch. By introducing unit aging rate correction into the standard coal consumption forecast for heating and power generation through the energy supply forecast module 202, it can accurately reflect the equipment efficiency decline and improve the reliability of heating and power supply capacity forecast. Through the dispatch model construction module 203, a two-level energy dispatch model of district / county-city is constructed and solved through the energy dispatch module 204, which can realize layered and zoned optimized dispatch, effectively reduce energy transmission costs, and improve system operating efficiency.

[0118] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0119] Based on the above-described embodiment of a provincial energy balance optimization scheduling method, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a provincial energy balance optimization scheduling method according to any embodiment of the present invention.

[0120] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0121] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0122] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0123] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the provincial energy balance optimization scheduling method described in any of the above-described method embodiments of the present invention.

[0124] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0125] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A provincial energy balance optimization scheduling method, characterized in that, include: Electricity consumption is predicted based on the electricity consumption characteristics of various industries over a preset time period. Based on the electricity consumption prediction results and the energy structure of each industry, the provincial energy consumption is calculated. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county. Based on the energy supply weight, energy production and energy import of each district and county, a preliminary forecast of the energy supply of each city and each county is made. Then, the heat supply and power supply are predicted based on the standard coal consumption for heating and standard coal consumption for power supply, and added to the preliminary forecast results to obtain the energy supply of each city and each county. A two-tier energy dispatch model is constructed based on the energy consumption of each city and each county, as well as the energy supply of each city and each county. The two-tier energy dispatch model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints. The two-layer energy dispatch model is solved hierarchically using a solver to generate provincial energy dispatch instructions, and the provincial energy network of the target province is controlled to perform energy dispatch according to the provincial energy dispatch instructions. The process involves forecasting electricity consumption based on the electricity consumption characteristics of various industries over a preset time period, and calculating the provincial energy consumption based on the forecast results and the energy structure of each industry. Then, based on the city and county-level energy consumption structures of each industry, the provincial energy consumption is further decomposed into city-level and county-level energy consumption, including: Based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. Based on the energy consumption of the first province and the energy structure of each industry, energy conversion is performed to obtain the energy consumption of the province. Based on the city and county structure of energy consumption of each industry, the energy consumption of each city and the energy consumption of each county are calculated respectively. The city-level and county-level energy consumption structures based on various industries are used to calculate the energy consumption of each city and each county, including: The city-level structure of energy consumption in each industry during the preset time period is weighted and smoothed to obtain the city-level structure of energy consumption in each industry. Based on the structure of each city, the energy consumption of the province is decomposed into the energy consumption of each city in the target province. Based on the industry electricity consumption growth trend, the first county-level structure of energy consumption of each industry in the preset time period is modified to obtain the county-level structure of energy consumption of each industry. Based on the structure of each district and county, the energy consumption of each city is decomposed into each district and county to obtain the energy consumption of each county in the target province. The preliminary forecast of energy supply for each city and county is made based on the energy supply weight, energy production, and energy import volume of each district and county. Then, the heating and electricity supply are predicted based on the standard coal consumption for heating and electricity supply, and these predictions are added to the preliminary forecast results to obtain the energy supply for each city and county, including: The data of each energy supply capacity indicator are weighted in layers to obtain multiple energy supply weights for each district and county. Based on the energy supply weights, energy production and energy imports, the supply volume is predicted to obtain the energy supply volume of each first municipal area and each first county area. Based on the unit aging rate correction, the standard coal consumption for heating and power supply are used to predict the heating and power supply respectively. The prediction results are then added to the energy supply of each first city area and each first county area to obtain the energy supply of each city area and each county area.

2. The provincial energy balance optimization scheduling method as described in claim 1, characterized in that, The electricity consumption characteristics of various industries based on a preset time period are used to cluster the industries in the target province into multiple industry groups. A grey prediction model based on ARIMA residual correction is then used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province, including: Collect the electricity consumption of the first industry in each industry of the target province within the preset time period; Features are extracted from the electricity consumption of each of the first industries to obtain the industry electricity consumption characteristics of each industry; wherein, the industry electricity consumption characteristics include the industry electricity consumption compound growth rate, the industry annual fluctuation range, the industry electricity consumption contribution ratio, and the industry electricity consumption proportion trend characteristics. Based on the electricity consumption characteristics of each industry, the K-Means algorithm is used for clustering to obtain multiple industry groups; wherein, the number of industry groups is determined according to the profile coefficient of each industry. The grey prediction model is used to predict the electricity consumption of each industry group, and the corresponding electricity consumption of multiple first industry groups is obtained. The ARIMA model is used to correct the residuals of the electricity consumption of each first industry group, and the corresponding electricity consumption of multiple industry groups is obtained. Based on the electricity consumption data of each industry group and the proportion of each industry in the corresponding industry group, the industry electricity consumption of each industry is calculated, and the electricity consumption of all industries is added together to obtain the first provincial energy consumption of the target province.

3. The provincial energy balance optimization scheduling method as described in claim 2, characterized in that, The energy conversion based on the energy consumption of the first province and the energy structure of each industry to obtain the provincial energy consumption includes: The ARIMA model is used to fit the trend of the energy structure of each industry during the preset time period to obtain multiple first energy conversion ratios for each industry; wherein, the first energy conversion ratio corresponds to one of four energy sources: coal, oil, natural gas and heat. Based on the amount of electricity substitution during the preset time period, the conversion ratio of each of the first energy sources is adjusted to obtain multiple energy conversion ratios for each of the industries. Energy consumption is calculated based on the energy consumption of the first province and the energy conversion ratios of each province to obtain the energy consumption of multiple second provinces. The energy consumption of the first province is then added to the energy consumption of each of the second provinces to obtain the energy consumption of the target province.

4. The provincial energy balance optimization scheduling method as described in claim 1, characterized in that, The data on various energy supply capacity indicators are weighted hierarchically to obtain multiple energy supply weights for each district and county. Based on these energy supply weights, energy production, and energy imports, supply forecasts are made to obtain the energy supply for each first municipality and each first county, including: Data on energy supply capacity indicators, energy imports, energy production, and energy production of each district and county in the target province during the preset time period are collected to determine multiple energy supply weights for each district and county, as well as the predicted values ​​of energy imports, energy production, and energy production. According to the energy supply weights mentioned above, the provincial energy transfer volume is decomposed to each city and each district and county, and then added to the corresponding energy production of each city and each county to obtain the energy supply of each second city and each second county. Based on the multiple first energy processing and conversion ratios within the preset time period, the energy supply of each second municipality and the energy supply of each second county are decomposed into energy processing and conversion amounts for each municipality, energy supply for each first municipality, energy processing and conversion amounts for each county, and energy supply for each first county.

5. The provincial energy balance optimization scheduling method as described in claim 4, characterized in that, The standard coal consumption for heating and power generation, corrected based on the unit aging rate, are used to predict heat supply and power generation, respectively. The prediction results are then added to the corresponding energy supply amounts for each of the first municipalities and the first counties to obtain the energy supply amounts for each municipality and each county, including: The standard coal consumption, heat supply and power supply of each unit in the target province during the preset time period are collected to calculate the first standard coal consumption for heat supply and the first standard coal consumption for power supply of each unit. The first standard coal consumption for heat supply and the first standard coal consumption for power supply are corrected according to the aging rate of each unit to obtain the standard coal consumption for heat supply and the standard coal consumption for power supply of each unit. Based on the energy processing and conversion volume of each city and each county, the energy supply of each second city and each second county, as well as the energy supply of each third city and each third county, are calculated using the standard coal consumption for heating and the standard coal consumption for power supply, respectively. The energy supply of each of the first municipalities, the energy supply of each of the second municipalities, and the energy supply of each of the third municipalities are added together to obtain the energy supply of each municipality. The energy supply of each of the first county, the energy supply of each of the second county, and the energy supply of each of the third county are added together to obtain the energy supply of each county.

6. The provincial energy balance optimization scheduling method as described in claim 1, characterized in that, The construction of a two-tier energy dispatch model based on the energy consumption of each city and each county, as well as the energy supply of each city and each county, includes: The energy consumption of each county is compared with the corresponding energy supply of each county to determine the first energy balance of the corresponding county, and the energy consumption of each city is compared with the corresponding energy supply of each city to determine the second energy balance of the corresponding city. A first energy dispatch model is constructed based on each of the first energy balance situations, and a second energy dispatch model is constructed based on each of the second energy balance situations. The first energy dispatch model is used as the first layer, and the second energy dispatch model is used as the second layer to construct a two-layer energy dispatch model.

7. A provincial energy balance optimization scheduling device, characterized in that, include: Energy consumption forecasting module, energy supply forecasting module, scheduling model construction module, and energy scheduling module; The energy consumption forecasting module is used to forecast electricity consumption based on the electricity consumption characteristics of various industries over a preset time period, and to calculate the provincial energy consumption based on the electricity consumption forecasting results and the energy structure of each industry. Then, based on the city and county structure of energy consumption in each industry, the provincial energy consumption is decomposed into the energy consumption of each city and the energy consumption of each county. The energy supply forecasting module is used to make preliminary forecasts of the energy supply of each city and each county based on the energy supply weight, energy production and energy import of each district and county. Then, it forecasts the heat supply and power supply based on the standard coal consumption for heating and the standard coal consumption for power supply and adds them to the preliminary forecast results to obtain the energy supply of each city and each county. The scheduling model construction module is used to construct a two-layer energy scheduling model based on the energy consumption of each city and the energy consumption of each county, as well as the energy supply of each city and the energy supply of each county; wherein, the two-layer energy scheduling model aims to minimize the total amount of flowing energy, and the constraints are supply constraints and channel capacity constraints; The energy dispatch module is used to solve the two-layer energy dispatch model in layers using a solver, generate provincial energy dispatch instructions, and control the provincial energy network of the target province to perform energy dispatch according to the provincial energy dispatch instructions. The process involves forecasting electricity consumption based on the electricity consumption characteristics of various industries over a preset time period, and calculating the provincial energy consumption based on the forecast results and the energy structure of each industry. Then, based on the city and county-level energy consumption structures of each industry, the provincial energy consumption is further decomposed into city-level and county-level energy consumption, including: Based on the electricity consumption characteristics of various industries over a preset time period, the industries in the target province are clustered into multiple industry groups, and a grey prediction model based on ARIMA residual correction is used to predict the electricity consumption of each industry group to obtain the energy consumption of the first province. Based on the energy consumption of the first province and the energy structure of each industry, energy conversion is performed to obtain the energy consumption of the province. Based on the city and county structure of energy consumption of each industry, the energy consumption of each city and the energy consumption of each county are calculated respectively. The city-level and county-level energy consumption structures based on various industries are used to calculate the energy consumption of each city and each county, including: The city-level structure of energy consumption in each industry during the preset time period is weighted and smoothed to obtain the city-level structure of energy consumption in each industry. Based on the structure of each city, the energy consumption of the province is decomposed into the energy consumption of each city in the target province. Based on the industry electricity consumption growth trend, the first county-level structure of energy consumption of each industry in the preset time period is modified to obtain the county-level structure of energy consumption of each industry. Based on the structure of each district and county, the energy consumption of each city is decomposed into each district and county to obtain the energy consumption of each county in the target province. The preliminary forecast of energy supply for each city and county is made based on the energy supply weight, energy production, and energy import volume of each district and county. Then, the heating and electricity supply are predicted based on the standard coal consumption for heating and electricity supply, and these predictions are added to the preliminary forecast results to obtain the energy supply for each city and county, including: The data of each energy supply capacity indicator are weighted in layers to obtain multiple energy supply weights for each district and county. Based on the energy supply weights, energy production and energy imports, the supply volume is predicted to obtain the energy supply volume of each first municipal area and each first county area. Based on the unit aging rate correction, the standard coal consumption for heating and power supply are used to predict the heating and power supply respectively. The prediction results are then added to the energy supply of each first city area and each first county area to obtain the energy supply of each city area and each county area.

Images