Industry-level power load dispatching method based on long-term and short-term load analysis

Abstract

The invention relates to the technical field of power load dispatching, in particular to an industry-level power load dispatching method based on long and short term load analysis, which comprises the following steps: S1, acquiring historical power consumption data, historical GDP growth rate and historical environment data of each power consumption industry in a target city; s2, calculating an electricity utilization elastic coefficient and a temperature sensitivity coefficient of each electricity utilization industry; s3, calculating a basic load prediction value of each power utilization industry; s4, predicting a short-term load prediction value and a long-term load prediction value of each electricity consumption industry through a machine learning model, and calculating a long-term and short-term load difference value; and S5, correspondingly calculating a power load optimization strategy of each power utilization industry based on the long-term and short-term load difference value of each power utilization industry in combination with the total power resource, and realizing power load adjustment of the corresponding power utilization industry based on the power load optimization strategy of each power utilization industry. According to the invention, the overall operation efficiency and reliability of the power system can be improved, and accurate distribution of industry-level power loads is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power load scheduling, in particular to an industry-level power load scheduling method based on long-term and short-term load analysis. BACKGROUND

[0002] The current urban power load scheduling generally adopts a "total balance" mode, focusing on the dynamic adjustment of the overall load curve of the power grid, and less on the fine description of the electricity consumption characteristics. Traditional scheduling systems are mostly based on historical electricity consumption data to construct prediction models, rarely integrating GDP growth rate, industrial electricity structure and other social and economic behavior data, and even more lacking in dynamic response mechanism to environmental factors such as temperature and humidity, resulting in a "one-size-fits-all" phenomenon in load distribution, which is difficult to meet the differentiated electricity demand.

[0003] Although the existing load scheduling schemes considering social and economic behaviors have realized the influence of economic activities and environmental factors on power load, they still have significant limitations. For example, some schemes attempt to include GDP growth rate in the load prediction model, but fail to distinguish the electricity consumption elasticity differences of different industries such as real estate, industry, transportation, wholesale and retail, information technology, accommodation and catering, agriculture, construction, finance, etc. In addition, the general lack of long-term and short-term prediction coordination mechanism leads to the disconnection between short-term load fluctuations and long-term trend prediction, making it difficult to support accurate scheduling decisions.

[0004] The applicant found that the core role of industry-level power load scheduling is to achieve optimal allocation of power resources through industry characteristic analysis. For example, industrial electricity consumption has continuity and high reliability requirements, while commercial electricity consumption is easily affected by holidays and promotional activities, showing impulsive fluctuations. Through industry-level differentiated scheduling, the flexibility of the power system can be improved, such as prioritizing power supply for key industries such as transportation during power shortages, and guiding industrial users to adjust production plans during peak renewable energy output periods to achieve the dual goals of "peak load shifting" and energy saving and emission reduction. However, the existing technology mainly has the following problems in industry-level power load scheduling: 1) insufficient industry characteristic analysis, failing to quantify the response differences of different industries to economic and environmental factors; 2) lack of deep multi-factor coupling relationship, such as the fact that GDP growth has a stronger pulling effect on industrial electricity consumption than on commercial electricity consumption, but traditional models often ignore such industry heterogeneity; 3) lack of long-term and short-term prediction coordination mechanism, making it difficult for short-term prediction to capture the surge in holiday commercial load and for long-term prediction to reflect the load trend changes caused by industrial structure adjustment.

[0005] In summary, the above problems restrict the improvement of power system operation efficiency and reliability, and it is urgent to achieve breakthroughs through industry-level power load scheduling technology. SUMMARY

[0006] To address the shortcomings of the existing technologies, the technical problem to be solved by this invention is: how to provide an industry-level power load dispatching method based on long-term and short-term load analysis, while considering the impact of cyclical fluctuations in GDP growth rate and environmental changes on industry-level power load dispatching, and taking into account both short-term supply and demand balance and long-term industrial power consumption structure optimization in power load dispatching, thereby improving the overall operating efficiency and reliability of the power system and achieving precise allocation of urban industry-level power load.

[0007] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0008] Industry-level power load dispatching methods based on long-term and short-term load analysis include:

[0009] S1: Obtain historical electricity consumption data, historical GDP growth rate, and historical environmental data for various electricity-consuming industries in the target city;

[0010] S2: Calculate the electricity consumption elasticity coefficient and temperature sensitivity coefficient for each electricity-consuming industry based on historical electricity consumption data, historical GDP growth rate and historical environmental data;

[0011] S3: Calculate the basic load forecast value for each electricity-consuming industry based on the electricity consumption elasticity coefficient and temperature sensitivity coefficient of each industry;

[0012] S4: Using machine learning models, predict the short-term and long-term load forecasts for each electricity-consuming industry based on the basic load forecasts for each industry, and calculate the difference between the short-term and long-term loads for each industry based on the short-term and long-term load forecasts for each industry.

[0013] S5: Based on the long-term and short-term load differences of various electricity-consuming industries and the total power resources, calculate the power load optimization strategy for each electricity-consuming industry, and implement power load regulation for the electricity-consuming industries based on the power load optimization strategy for each electricity-consuming industry.

[0014] Preferably, in step S2, the processing steps for calculating the electricity consumption elasticity coefficient and temperature sensitivity coefficient for each electricity-consuming industry include:

[0015] S201: Construct an electrical elasticity-temperature sensitive model;

[0016] The formula is expressed as:

[0017] ;

[0018] In the formula: Indicates the first individual electricity consumption industries Electricity consumption at any given time; Indicates the first individual electricity consumption industries GDP growth rate at any given time; Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Represents the residual term;

[0019] S202: The electricity elasticity-temperature sensitivity model is fitted using the least squares method based on historical electricity consumption data, historical GDP growth rate, and historical environmental data for each electricity-consuming industry, yielding the electricity elasticity coefficients for each industry. and temperature sensitivity coefficient .

[0020] Preferably, in step S3, the base load forecast value for each electricity-consuming industry is calculated using the following formula:

[0021] ;

[0022] In the formula: Indicates the first individual electricity consumption industries The base load forecast value at that time; This indicates the initial load value set. Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Indicates the first Temperature thresholds for individual electricity-consuming industries; express The real ambient temperature at any given moment; This indicates the number of industries that consume electricity.

[0023] Preferably, in step S3, the following formula is used to calculate... The actual ambient temperature at any given moment:

[0024] ;

[0025] ;

[0026] ;

[0027] In the formula: Indicates the daily average temperature; The set temperature threshold; Relative humidity correction term; This indicates the wind force level correction item; This indicates the sunshine duration correction item. This indicates the set solar radiation coefficient; This indicates relative humidity.

[0028] Preferably, in step S4, the processing steps for predicting the short-term and long-term load forecasts for each electricity-consuming industry include:

[0029] S401: Based on the basic load forecast values ​​of various electricity-consuming industries Calculate the total base load forecast for all electricity-consuming industries;

[0030] The formula is expressed as:

[0031] ;

[0032] In the formula: express Total base load forecast at any given time; This indicates the number of industries consuming electricity;

[0033] S402: Input the total base load forecast and the total GDP growth rate of all electricity-consuming industries into the trained LSTM model, and output the corresponding short-term load forecast.

[0034] The formula is expressed as:

[0035] ;

[0036] ;

[0037] In the formula: express Short-term load forecast values ​​at any given time; This represents the trained LSTM model. This represents the trained weight parameters in the LSTM model; This represents the input to the LSTM model; This represents the total GDP growth rate of all electricity-consuming industries; The symbol indicates a holiday; 1 represents a holiday and 0 represents a non-holiday.

[0038] S403: Input the total base load forecast, the industrial structure adjustment coefficient and urbanization rate of the target city into the trained support vector machine model, and output the corresponding long-term load forecast.

[0039] The formula is expressed as:

[0040] ;

[0041] In the formula: This represents the long-term load forecast. This represents the trained support vector machine model; This represents the industrial structure adjustment coefficient of the target city; This indicates the urbanization rate of the target city.

[0042] Preferably, step S4 further includes the following steps:

[0043] S404: Calculate the short-term industry-level load value for each electricity-consuming industry based on the short-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry;

[0044] The formula is expressed as:

[0045] ;

[0046] In the formula: Indicates the first One in Short-term industry-level load values ​​at any given time;

[0047] S405: Calculate the long-term industry-level load value for each electricity-consuming industry based on the long-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry.

[0048] The formula is expressed as:

[0049] ;

[0050] In the formula: Indicates the first individual electricity consumption industries Long-term industry-level load values ​​at any given time;

[0051] S406: Calculate the difference between short-term and long-term load values ​​for each electricity-consuming industry based on its short-term and long-term industry-level load values.

[0052] The formula is expressed as:

[0053] ;

[0054] In the formula: Indicates the first individual electricity consumption industries The difference between short-term and long-term loads at any given time.

[0055] Preferably, in step S5, the steps for calculating the power load optimization strategy for each electricity-consuming industry include:

[0056] S501: Calculate the regulation sensitivity index of each electricity-consuming industry based on the long-term and short-term load differences, long-term industry-level load values, and electricity consumption elasticity coefficients.

[0057] The formula is expressed as:

[0058] ;

[0059] In the formula: Indicates the first individual electricity consumption industries The sensitivity index to adjustment at any given moment;

[0060] S502: Calculate the allocated power resources for each power-consuming industry based on the total power resources and the regulation sensitivity index of each power-consuming industry.

[0061] The formula is expressed as:

[0062] ;

[0063] In the formula: Indicates the first individual electricity consumption industries The allocation of power resources at all times; Indicates the total available power resources; This indicates the number of industries consuming electricity;

[0064] S503: For electricity-consuming industries where the difference between long-term and short-term loads is greater than the set load threshold, calculate the reduction in electricity load for that industry;

[0065] The formula is expressed as:

[0066] ;

[0067] In the formula: Indicates the first individual electricity consumption industries Reduce electricity load at all times;

[0068] S504: Allocate power resources and reduce power load for each power-consuming industry as its corresponding power load optimization strategy.

[0069] Preferably, step S4 further includes the following steps:

[0070] S407: Weighted fusion of short-term and long-term load forecasts to generate a comprehensive load forecast;

[0071] The formula is expressed as:

[0072] ;

[0073] In the formula: express The comprehensive load forecast value at any given time; express Weighting coefficients at different times.

[0074] Preferably, in step S4, the weighting coefficient is adjusted based on the long-term and short-term load differences and long-term industry-level load values ​​of various electricity-consuming industries. ;

[0075] The formula is expressed as:

[0076] ;

[0077] In the formula: This represents the initial fusion weights.

[0078] Preferably, step S5 further includes the following steps:

[0079] S505: Calculate the total electricity load adjustment for all electricity-consuming industries based on the reduction of electricity load in each industry;

[0080] The formula is expressed as:

[0081] ;

[0082] In the formula: express The total power load adjustment at any given time;

[0083] S505: Calculate the deviation rate based on the total power load adjustment and the comprehensive load forecast value: If the deviation rate is less than the set deviation threshold, output the power load optimization strategy for each power-consuming industry; otherwise, return to step S502 and adjust the power resource allocation for each power-consuming industry.

[0084] The formula for calculating the deviation rate is as follows:

[0085] ;

[0086] In the formula: express The deviation rate at any given time.

[0087] Compared with existing technologies, the industry-level power load dispatching method based on long-term and short-term load analysis in this invention has the following advantages:

[0088] This invention constructs a two-dimensional load forecasting model based on GDP growth and environmental data through dynamic calculation of the electricity elasticity coefficient and temperature sensitivity coefficient. This load forecasting model integrates multi-source heterogeneous data such as industry GDP growth rate and temperature threshold correction value, breaking through the limitations of traditional single load forecasting. Among them, the electricity elasticity coefficient quantifies the coupling relationship between industry electricity consumption and GDP growth, reflecting the real demand elasticity of industry production activities for electricity. For example, the sensitivity of high-energy-consuming industries to GDP growth is significantly higher than that of the service industry. This differentiated modeling method can accurately reflect the driving mechanism of electricity demand in different industries. The temperature sensitivity coefficient, on the other hand, quantifies the nonlinear impact of environmental factors on electricity consumption behavior, taking into account the unique environmental response characteristics of each industry. For example, the electricity consumption of industries such as metallurgy and chemicals is less affected by temperature fluctuations, while the electricity consumption of commercial air conditioning and refrigeration equipment is strongly correlated with temperature. By using the synergistic effect of the electrical elasticity coefficient and the temperature sensitivity coefficient to characterize the dynamic characteristics of industry-level loads, the generated basic load forecast values ​​include both the endogenous driving force of GDP growth rate fluctuations and the external disturbances of environmental changes. This provides a quantifiable basis for industry-level power dispatch, thereby enhancing the ability to optimize the allocation of power resources among industries and achieving precise allocation of industry-level power loads.

[0089] This invention integrates machine learning models to predict short-term and long-term loads, constructing a GDP-environment dual-factor driven load optimization strategy. The LSTM model captures the temporal characteristics of short-term loads (e.g., daily / weekly loads), combining data such as holidays and GDP growth rate to achieve accurate predictions from minute to day. The support vector machine model focuses on the structural changes in long-term loads (e.g., monthly / yearly loads), incorporating indicators such as industrial structure adjustment coefficients and urbanization rates to form cross-cycle load trend judgments. The difference between the two models reflects the uncertainty of industry-level electricity demand. Simultaneously, by calculating the difference between short-term and long-term loads, the invention reflects the contradictions and synergies in industry electricity demand at different time scales. Combined with the dynamic allocation of total power resources, a two-way optimization mechanism of "short-term peak shaving and long-term structural adjustment" is formed. This mechanism achieves precise industry-level allocation and scheduling of power resources by adjusting the sensitivity index, ensuring short-term supply and demand balance while guiding long-term industrial electricity structure optimization, thereby improving the overall operating efficiency and reliability of the power system. Attached Figure Description

[0090] To make the objectives, technical solutions, and advantages of the invention clearer, the invention will now be described in further detail with reference to the accompanying drawings, wherein:

[0091] Figure 1 This is a logic block diagram of an industry-level power load dispatching method based on long-term and short-term load analysis. Detailed Implementation

[0092] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but only to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0093] It should be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the figures, or the orientation or positional relationship commonly used when the product is in use. They are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance. In addition, the terms "horizontal," "vertical," etc., do not mean that the component is required to be absolutely horizontal or suspended, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0094] The following detailed explanation illustrates the specific implementation methods:

[0095] Example:

[0096] This embodiment discloses an industry-level power load dispatching method based on long-term and short-term load analysis.

[0097] likeFigure 1 As shown, the industry-level power load dispatching method based on long-term and short-term load analysis includes:

[0098] S1: Obtain historical electricity consumption data, historical GDP (Gross Domestic Product) growth rate, and historical environmental data for various electricity-consuming industries in the target city;

[0099] S2: Calculate the electricity consumption elasticity coefficient and temperature sensitivity coefficient for each electricity-consuming industry based on historical electricity consumption data, historical GDP growth rate and historical environmental data;

[0100] S3: Calculate the basic load forecast value for each electricity-consuming industry based on the electricity consumption elasticity coefficient and temperature sensitivity coefficient of each industry;

[0101] S4: Using machine learning models, predict the short-term and long-term load forecasts for each electricity-consuming industry based on the basic load forecasts for each industry, and calculate the difference between the short-term and long-term loads for each industry based on the short-term and long-term load forecasts for each industry.

[0102] S5: Based on the long-term and short-term load differences of various electricity-consuming industries and the total power resources, calculate the power load optimization strategy for each electricity-consuming industry, and implement power load regulation for the electricity-consuming industries based on the power load optimization strategy for each electricity-consuming industry.

[0103] In the specific implementation process, the steps for calculating the electricity consumption elasticity coefficient and temperature sensitivity coefficient for various electricity-consuming industries include:

[0104] S201: Construct an electrical elasticity-temperature sensitive model;

[0105] The formula is expressed as:

[0106] ;

[0107] In the formula: Indicates the first individual electricity consumption industries Electricity consumption at any given time; Indicates the first individual electricity consumption industries GDP growth rate at any given time; Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Represents the residual term, used to indicate factors that are not modeled (such as policy adjustments);

[0108] S202: The electricity elasticity-temperature sensitivity model is fitted using the least squares method based on historical electricity consumption data, historical GDP growth rate, and historical environmental data for each electricity-consuming industry, yielding the electricity elasticity coefficients for each industry. and temperature sensitivity coefficient .

[0109] In the specific implementation process, the basic load forecast values ​​for each electricity-consuming industry are calculated using the following formula:

[0110] ;

[0111] In the formula: Indicates the first individual electricity consumption industries The base load forecast value at that time; This indicates the initial load value set. Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Indicates the first Temperature thresholds for individual electricity-consuming industries; express The real ambient temperature at any given moment; This indicates the number of industries consuming electricity, including real estate, manufacturing, transportation, wholesale and retail, information technology, accommodation and catering, agriculture, construction, and finance.

[0112] Specifically, it is calculated using the following formula. The actual ambient temperature at any given moment:

[0113] ;

[0114] ;

[0115] ;

[0116] In the formula: Indicates the daily average temperature; The set temperature threshold is 10℃; Relative humidity correction term; This indicates the wind speed level correction factor; for each increase of one level in wind speed, Temperature dropped by 1.2℃; This indicates the sunshine duration correction item. This indicates the set solar radiation coefficient; This indicates relative humidity.

[0117] In the specific implementation process, the processing steps for predicting the short-term and long-term load forecasts for various electricity-consuming industries include:

[0118] S401: Based on the basic load forecast values ​​of various electricity-consuming industries Calculate the total base load forecast for all electricity-consuming industries;

[0119] The formula is expressed as:

[0120] ;

[0121] In the formula: express Total base load forecast at any given time; This indicates the number of industries consuming electricity;

[0122] S402: Input the total base load forecast and the total GDP growth rate of all electricity-consuming industries into the trained LSTM model, and output the corresponding short-term load forecast.

[0123] The formula is expressed as:

[0124] ;

[0125] ;

[0126] In the formula: express Short-term load forecast values ​​at any given time; This represents the trained LSTM model. This represents the trained weight parameters in the LSTM model; This represents the input to the LSTM model; This represents the total GDP growth rate of all electricity-consuming industries; The symbol indicates a holiday; 1 represents a holiday and 0 represents a non-holiday.

[0127] S403: Input the total base load forecast, the industrial structure adjustment coefficient and urbanization rate of the target city into the trained support vector machine model, and output the corresponding long-term load forecast.

[0128] In this embodiment, the data source for the industrial structure adjustment coefficient is the "proportion of added value of the tertiary industry" and the "proportion of added value of the secondary industry" of the target city; the calculation formula is: industrial structure adjustment coefficient = proportion of added value of the tertiary industry - proportion of added value of the secondary industry; if the result is negative, the coefficient is 0 (indicating that the industrial structure has not been transformed); this coefficient reflects the extent to which the city is transforming towards high value-added industries, and the larger the value, the more significant the transformation; if the coefficient exceeds 10%, it can be given a higher weight in the model.

[0129] The data source for urbanization rate is the "urban resident population" and "total population" data of the target city; the calculation formula is: urbanization rate = (urban resident population / total population) × 100%.

[0130] Neither parameter requires additional data collection. The urbanization rate is directly related to the impact of population growth on load, while the industrial structure adjustment coefficient quantifies the driving force of economic structure changes on electricity demand. Combining the two can improve the accuracy of long-term load forecasting.

[0131] The formula is expressed as:

[0132] ;

[0133] In the formula: This represents the long-term load forecast. This represents the trained support vector machine model; This represents the industrial structure adjustment coefficient of the target city; This indicates the urbanization rate of the target city.

[0134] This invention uses the industrial structure adjustment coefficient and urbanization rate of the target city as inputs to a support vector machine model to predict long-term load. The industrial structure adjustment coefficient reflects the degree to which a city is transforming from high-energy-consuming industries (such as heavy industry) to low-energy-consuming industries (such as services and high-tech industries); the urbanization rate reflects the direct impact of urban population growth on residential electricity consumption, commercial electricity consumption, and infrastructure electricity demand (such as elevators, lighting, and air conditioning). Both are core drivers of long-term load, complementing historical load data and GDP growth rates, thus avoiding prediction biases caused by relying solely on short-term economic indicators.

[0135] S404: Calculate the short-term industry-level load value for each electricity-consuming industry based on the short-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry;

[0136] The formula is expressed as:

[0137] ;

[0138] In the formula: Indicates the first One in Short-term industry-level load values ​​at any given time;

[0139] S405: Calculate the long-term industry-level load value for each electricity-consuming industry based on the long-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry.

[0140] The formula is expressed as:

[0141] ;

[0142] In the formula: Indicates the first individual electricity consumption industries Long-term industry-level load values ​​at any given time;

[0143] S406: Calculate the difference between short-term and long-term load values ​​for each electricity-consuming industry based on its short-term and long-term industry-level load values.

[0144] The formula is expressed as:

[0145] ;

[0146] In the formula: Indicates the first individual electricity consumption industries The difference between short-term and long-term loads at any given time.

[0147] S407: Weighted fusion of short-term and long-term load forecasts to generate a comprehensive load forecast;

[0148] The formula is expressed as:

[0149] ;

[0150] In the formula: express The comprehensive load forecast value at any given time; express Weighting coefficients at different times.

[0151] Specifically, the weighting coefficients are adjusted based on the differences between short-term and long-term loads in various electricity-consuming industries and the long-term industry-level load values. ;

[0152] The formula is expressed as:

[0153] ;

[0154] In the formula: This represents the initial fusion weight (set to 0.5).

[0155] In the specific implementation process, the steps for calculating the power load optimization strategy for each electricity-consuming industry include:

[0156] S501: Calculate the regulation sensitivity index of each electricity-consuming industry based on the long-term and short-term load differences, long-term industry-level load values, and electricity consumption elasticity coefficients.

[0157] The formula is expressed as:

[0158] ;

[0159] In the formula: Indicates the first individual electricity consumption industries The sensitivity index to adjustment at any given moment;

[0160] S502: Calculate the allocated power resources for each power-consuming industry based on the total power resources and the regulation sensitivity index of each power-consuming industry.

[0161] The formula is expressed as:

[0162] ;

[0163] In the formula: Indicates the first individual electricity consumption industries The allocation of electrical resources (power) at any given time; Indicates the total available power resources; This indicates the number of industries consuming electricity;

[0164] S503: For electricity-consuming industries where the difference between long-term and short-term loads is greater than the set load threshold, calculate the reduction of electricity load (peak shaving instruction) for that industry.

[0165] The formula is expressed as:

[0166] ;

[0167] In the formula: Indicates the first individual electricity consumption industries Peak shaving command (timely reduction of electricity load);

[0168] S504: Allocate power resources and reduce power load (peak shaving command) for each power-consuming industry as its corresponding power load optimization strategy.

[0169] S505: Calculate the total electricity load adjustment for all electricity-consuming industries based on the electricity load reduction (peak shaving command) of each industry;

[0170] The formula is expressed as:

[0171] ;

[0172] In the formula: express The total power load adjustment at any given time;

[0173] S505: Calculate the deviation rate based on the total power load adjustment and the comprehensive load forecast value: If the deviation rate is less than the set deviation threshold (set to 5%), output the power load optimization strategy for each power-consuming industry; otherwise, return to step S502 and (manually) adjust the power allocation resources for each power-consuming industry.

[0174] The formula for calculating the deviation rate is as follows:

[0175] ;

[0176] In the formula: express The deviation rate at any given time.

[0177] This invention constructs a two-dimensional load forecasting model based on GDP growth and environmental data through dynamic calculation of the electricity elasticity coefficient and temperature sensitivity coefficient. This load forecasting model integrates multi-source heterogeneous data such as industry GDP growth rate and temperature threshold correction value, breaking through the limitations of traditional single load forecasting. Among them, the electricity elasticity coefficient quantifies the coupling relationship between industry electricity consumption and GDP growth, reflecting the real demand elasticity of industry production activities for electricity. For example, the sensitivity of high-energy-consuming industries to GDP growth is significantly higher than that of the service industry. This differentiated modeling method can accurately reflect the driving mechanism of electricity demand in different industries. The temperature sensitivity coefficient, on the other hand, quantifies the nonlinear impact of environmental factors on electricity consumption behavior, taking into account the unique environmental response characteristics of each industry. For example, the electricity consumption of industries such as metallurgy and chemicals is less affected by temperature fluctuations, while the electricity consumption of commercial air conditioning and refrigeration equipment is strongly correlated with temperature. By using the synergistic effect of the electrical elasticity coefficient and the temperature sensitivity coefficient to characterize the dynamic characteristics of industry-level loads, the generated basic load forecast values ​​include both the endogenous driving force of GDP growth rate fluctuations and the external disturbances of environmental changes. This provides a quantifiable basis for industry-level power dispatch, thereby enhancing the ability to optimize the allocation of power resources among industries and achieving precise allocation of industry-level power loads.

[0178] This invention integrates machine learning models to predict short-term and long-term loads, constructing a GDP-environment dual-factor driven load optimization strategy. The LSTM model captures the temporal characteristics of short-term loads (e.g., daily / weekly loads), combining data such as holidays and GDP growth rate to achieve accurate predictions from minute to day. The support vector machine model focuses on the structural changes in long-term loads (e.g., monthly / yearly loads), incorporating indicators such as industrial structure adjustment coefficients and urbanization rates to form cross-cycle load trend judgments. The difference between the two models reflects the uncertainty of industry-level electricity demand. Simultaneously, by calculating the difference between short-term and long-term loads, the invention reflects the contradictions and synergies in industry electricity demand at different time scales. Combined with the dynamic allocation of total power resources, a two-way optimization mechanism of "short-term peak shaving and long-term structural adjustment" is formed. This mechanism achieves precise industry-level allocation and scheduling of power resources by adjusting the sensitivity index, ensuring short-term supply and demand balance while guiding long-term industrial electricity structure optimization, thereby improving the overall operating efficiency and reliability of the power system.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit the technical solutions. Those skilled in the art should understand that any modifications or equivalent substitutions to the technical solutions of the present invention without departing from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. An industry-level power load dispatching method based on long-term and short-term load analysis, characterized in that, include: S1: Obtain historical electricity consumption data, historical GDP growth rate, and historical environmental data for various electricity-consuming industries in the target city; S2: Calculate the electricity consumption elasticity coefficient and temperature sensitivity coefficient for each electricity-consuming industry based on historical electricity consumption data, historical GDP growth rate and historical environmental data; S3: Calculate the basic load forecast value for each electricity-consuming industry based on the electricity consumption elasticity coefficient and temperature sensitivity coefficient of each industry; S4: Using machine learning models, predict the short-term and long-term load forecasts for each electricity-consuming industry based on the basic load forecasts for each industry, and calculate the difference between the short-term and long-term loads for each industry based on the short-term and long-term load forecasts for each industry. S5: Based on the long-term and short-term load differences of various electricity-consuming industries and the total power resources, calculate the power load optimization strategy for each electricity-consuming industry, and implement power load regulation for the electricity-consuming industries based on the power load optimization strategy for each electricity-consuming industry.

2. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 1, characterized in that: Step S2, the processing steps for calculating the electricity consumption elasticity coefficient and temperature sensitivity coefficient for each electricity-consuming industry include: S201: Construct an electrical elasticity-temperature sensitive model; The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries Electricity consumption at any given time; Indicates the first individual electricity consumption industries GDP growth rate at any given time; Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Represents the residual term; S202: The electricity elasticity-temperature sensitivity model is fitted using the least squares method based on historical electricity consumption data, historical GDP growth rate, and historical environmental data for each electricity-consuming industry, yielding the electricity elasticity coefficients for each industry. and temperature sensitivity coefficient .

3. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 2, characterized in that: In step S3, the base load forecast value for each electricity-consuming industry is calculated using the following formula: ； In the formula: Indicates the first individual electricity consumption industries The base load forecast value at that time; This indicates the initial load value set. Indicates the first Electricity consumption elasticity coefficient for each electricity-consuming industry; Indicates the first Temperature sensitivity coefficient of each electricity-consuming industry; Indicates the first Temperature thresholds for individual electricity-consuming industries; express The real ambient temperature at any given moment; This indicates the number of industries that consume electricity.

4. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 3, characterized in that: In step S3, the following formula is used to calculate... The actual ambient temperature at any given moment: ； ； ； In the formula: Indicates the daily average temperature; The set temperature threshold; Relative humidity correction term; This indicates the wind force level correction item; This indicates the sunshine duration correction item. This indicates the set solar radiation coefficient; This indicates relative humidity.

5. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 1, characterized in that: Step S4, the processing steps for predicting the short-term and long-term load forecasts for various electricity-consuming industries, include: S401: Based on the basic load forecast values ​​of various electricity-consuming industries Calculate the total base load forecast for all electricity-consuming industries; The formula is expressed as: ； In the formula: express Total base load forecast at any given time; This indicates the number of industries consuming electricity; S402: Input the total base load forecast and the total GDP growth rate of all electricity-consuming industries into the trained LSTM model, and output the corresponding short-term load forecast. The formula is expressed as: ； ； In the formula: express Short-term load forecast values ​​at any given time; This represents the trained LSTM model. This represents the trained weight parameters in the LSTM model; This represents the input to the LSTM model; This represents the total GDP growth rate of all electricity-consuming industries; The symbol indicates a holiday; 1 represents a holiday and 0 represents a non-holiday. S403: Input the total base load forecast, the industrial structure adjustment coefficient and urbanization rate of the target city into the trained support vector machine model, and output the corresponding long-term load forecast. The formula is expressed as: ； In the formula: This represents the long-term load forecast. This represents the trained support vector machine model; This represents the industrial structure adjustment coefficient of the target city; This indicates the urbanization rate of the target city.

6. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 5, characterized in that: Step S4 also includes the following steps: S404: Calculate the short-term industry-level load value for each electricity-consuming industry based on the short-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry; The formula is expressed as: ； In the formula: Indicates the first One in Short-term industry-level load values ​​at any given time; S405: Calculate the long-term industry-level load value for each electricity-consuming industry based on the long-term load forecast value and the electricity consumption elasticity coefficient of each electricity-consuming industry. The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries Long-term industry-level load values ​​at any given time; S406: Calculate the difference between short-term and long-term load values ​​for each electricity-consuming industry based on its short-term and long-term industry-level load values. The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries The difference between short-term and long-term loads at any given time.

7. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 6, characterized in that: Step S5, the steps for calculating the power load optimization strategy for each electricity-consuming industry, include: S501: Calculate the regulation sensitivity index of each electricity-consuming industry based on the long-term and short-term load differences, long-term industry-level load values, and electricity consumption elasticity coefficients. The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries The sensitivity index to adjustment at any given moment; S502: Calculate the allocated power resources for each power-consuming industry based on the total power resources and the regulation sensitivity index of each power-consuming industry. The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries The allocation of power resources at all times; Indicates the total available power resources; This indicates the number of industries consuming electricity; S503: For electricity-consuming industries where the difference between long-term and short-term loads is greater than the set load threshold, calculate the reduction in electricity load for that industry; The formula is expressed as: ； In the formula: Indicates the first individual electricity consumption industries Reduce electricity load at all times; S504: Allocate power resources and reduce power load for each power-consuming industry as its corresponding power load optimization strategy.

8. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 7, characterized in that: Step S4 also includes the following steps: S407: Weighted fusion of short-term and long-term load forecasts to generate a comprehensive load forecast; The formula is expressed as: ； In the formula: express The comprehensive load forecast value at any given time; express Weighting coefficients at different times.

9. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 8, characterized in that: In step S4, the weighting coefficient is adjusted based on the long-term and short-term load differences and long-term industry-level load values ​​of various electricity-consuming industries. ; The formula is expressed as: ； In the formula: This represents the initial fusion weights.

10. The industry-level power load dispatching method based on long-term and short-term load analysis as described in claim 8, characterized in that: Step S5 also includes the following steps: S505: Calculate the total electricity load adjustment for all electricity-consuming industries based on the reduction of electricity load in each industry; The formula is expressed as: ； In the formula: express The total power load adjustment at any given time; S505: Calculate the deviation rate based on the total power load adjustment and the comprehensive load forecast value: If the deviation rate is less than the set deviation threshold, output the power load optimization strategy for each power-consuming industry; Otherwise, return to step S502 to adjust the allocation of power resources for each power-consuming industry; The formula for calculating the deviation rate is as follows: ； In the formula: express The deviation rate at any given time.

Images