An intelligent power distribution network resource scheduling and real-time management method

Abstract

The application discloses a kind of intelligent power distribution network resource scheduling and real-time management method, it is related to power resource scheduling technical field, it is difficult to adaptively dispatch power according to the power consumption characteristics of region in power resource scheduling, and it is difficult to supply power to region according to the technical problems of the double power supply mode of "power grid+energy storage" appropriately;The application obtains the target data of each region and the record data of intelligent electric meter by dividing different time periods;Based on the environment of next time period, holiday days and factory planned capacity, the influence factors of residential, commercial and industrial electricity are calculated respectively;Combined with the characteristic power consumption of intelligent electric meter, the expected power consumption of next time period is obtained by adjusting the influence factor, the power supply capacity of power grid and the energy storage power supply strategy are determined according to the expected power consumption, and dynamic power allocation is realized;The application can solve the problems of inaccurate prediction and uneven resource allocation in traditional power dispatching, and improve the efficiency and stability of power grid operation.

Description

Technical Field

[0001] This invention belongs to the field of smart grids and relates to power resource dispatching technology, specifically an intelligent power distribution network resource dispatching and real-time management method. Background Technology

[0002] With the ever-increasing demand for electricity, power distribution networks are becoming increasingly important, making intelligent power distribution network resource scheduling and real-time management a crucial research topic. Current methods for power distribution network resource scheduling and real-time management suffer from several problems, such as low scheduling efficiency and uneven resource allocation.

[0003] Currently, most intelligent power distribution network resource scheduling and real-time management methods are unable to adaptively schedule power according to regional power consumption characteristics, and are unable to capture the evolution of regional power consumption behavior. This leads to a mismatch between predicted power allocation resources and actual demand. This mismatch not only causes energy waste and grid overload risks, but may also inhibit the efficient consumption of renewable energy and exacerbate grid stability pressures.

[0004] Therefore, this invention discloses an intelligent power distribution network resource scheduling and real-time management method to solve the above-mentioned technical problems. Summary of the Invention

[0005] This invention aims to solve at least one of the technical problems existing in the prior art. To this end, this invention proposes an intelligent power distribution network resource scheduling and real-time management method to address the technical problems of difficulty in adaptively scheduling power according to the regional power consumption characteristics and the difficulty in appropriately supplying power to a region according to the "grid + energy storage" dual power supply mode. This invention solves the above problems by dividing different time periods and obtaining target data and smart meter recording data for each region; calculating the impact factors of residential, commercial and industrial electricity consumption based on the environmental conditions, number of holidays and factory planned capacity for the next time period; combining the characteristic electricity consumption of smart meters, adjusting the impact factors to obtain the expected electricity consumption for the next time period; and determining the grid power supply and energy storage power supply strategy based on the expected electricity consumption, thereby achieving dynamic power allocation.

[0006] To achieve the above objectives, a first aspect of the present invention provides an intelligent power distribution network resource scheduling and real-time management method, comprising:

[0007] Divide time periods and power supply companies into several management areas;

[0008] The system sequentially acquires target data for each time period within the managed area, as well as recorded data from each smart meter. The target data includes temperature, humidity, number of holidays, and planned production capacity for each factory. The recorded data includes electricity consumption type and electricity consumption at each time point.

[0009] When the time reaches the first point of the current time period, the impact factors on residential electricity consumption are determined based on the temperature and humidity of the next time period.

[0010] The impact factors on commercial electricity consumption of each shopping mall are determined based on the number of holiday days in the next time period.

[0011] The industrial electricity consumption impact factors for each factory are determined based on planned production capacity;

[0012] Based on the recorded data, determine the characteristic electricity consumption recorded by the smart meter in the next time period;

[0013] The expected electricity consumption of the management area in the next time period is obtained by adjusting the characteristic electricity consumption based on environmental electricity consumption impact factors, commercial electricity consumption impact factors, or industrial electricity consumption impact factors.

[0014] Based on the projected electricity consumption, the grid supply for the next time period and the energy storage capacity for the current time period are determined, and the energy storage supply is adjusted in real time according to the grid supply in the next time period.

[0015] Preferably, the time period division and the power supply company's several management areas include:

[0016] The total area served by the power supply company is obtained, and individual factories, shopping malls, or residential communities within the total area are divided into independent management areas; areas within the total area that are not divided into management areas are manually planned into several management areas.

[0017] When the first day of each month arrives, the total energy storage capacity ZD of the previous month in the total region is obtained; when the total energy storage capacity ZD is less than the storage capacity threshold CZ, the month is divided into several time periods according to the standard duration BC; when the total energy storage capacity ZD is not less than the storage capacity threshold CZ, the formula DC= BC×ρ×CZ / ZD The dynamic duration DC is obtained, and the month is divided into several time periods according to the dynamic duration DC; among them, the storage power threshold CZ and the standard duration BC are both manually set. ρ is the floor sign; ρ is the scaling factor, and the value of ρ ranges from (0,1).

[0018] Preferably, the step of sequentially acquiring target data for each time period within the management area and recorded data from each smart meter includes:

[0019] Each management area is extracted sequentially, and several temperatures and humidity levels for each time period within the management area are obtained through a weather forecast platform;

[0020] The database is used to obtain the number of holidays this month and the planned production capacity of each factory in each time period; the smart meters are used to obtain the electricity consumption type and electricity consumption at each time point in the managed area; the electricity consumption type includes residential electricity, commercial electricity and industrial electricity.

[0021] Preferably, the determination of residential electricity consumption impact factors based on temperature and humidity in the next time period includes:

[0022] The target percentiles of several temperatures within each time period are marked as the characteristic temperature DW of the current time period, and the target percentiles of several humidity levels within each time period are marked as the characteristic humidity DS of the current time period; wherein, the percentiles in the target percentiles are obtained by manual setting.

[0023] Extract the characteristic temperature DW for the next time period, as well as the maximum value GW and minimum value LW of several temperatures within the next time period; when the characteristic temperature DW does not exceed the suitable temperature range, the residential electricity consumption impact factor is set to the standard electricity consumption impact factor BY; whereby the suitable temperature range is obtained artificially based on the human body's adaptation to various temperatures.

[0024] When the characteristic temperature DW is greater than the maximum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the maximum value GW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula:

[0025] ;

[0026] Where ZW is the midpoint of the suitable temperature range, and BS is the artificially set standard suitable humidity; and All of these are manually set proportional adjustment coefficients, and , ; The amplitude adjustment coefficient is set manually, and The value range is [0,1];

[0027] When the characteristic temperature DW is less than the minimum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the minimum value LW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula:

[0028] ;

[0029] in, and All of these are manually set proportional adjustment coefficients, and , .

[0030] Preferably, the determination of the commercial electricity consumption impact factor for each shopping mall based on the number of holiday days in the next time period includes:

[0031] Extract the number of holiday days RT in the next time period, the total number of days ZT in the next time period, and the average customer flow PL of the shopping mall during the current holiday in the historical data;

[0032] Based on the number of holiday days RT, the total number of days ZT, and the average passenger flow PL, the commercial electricity consumption impact factor SZ for the current commercial electricity consumption area in the next time period is determined; the commercial electricity consumption impact factor SZ satisfies the following formula:

[0033] ;

[0034] BPL is a manually set standard passenger flow. The ratio adjustment factor is set manually, and The value range is [0, 2].

[0035] Preferably, the determination of the industrial electricity consumption impact factor for each factory based on planned production capacity includes:

[0036] Extract the factory's planned capacity CN for the next time period, and the completion rate of the factory's planned capacity in each time period from historical data; integrate the completion rates of the planned capacity in each time period into a capacity completion rate group, and obtain the variance of the completion rate in the capacity completion rate group; determine whether the variance of the capacity completion rate group is less than the defined variance; if yes, calculate the average of the completion rates in the capacity completion rate group to obtain the current factory's characteristic completion rate TL; if no, remove the completion rate in the capacity completion rate group that differs the most from the mode of the completion rate, and re-determine the variance until the variance of the capacity completion rate group is less than the defined variance, and calculate the average of the remaining completion rates in the capacity completion rate group to obtain the current factory's characteristic completion rate TL; wherein, the defined variance is obtained by manual setting;

[0037] Multiply the planned capacity CN by the characteristic completion rate TL to obtain the industrial electricity consumption impact factor GZ of the current factory in the next time period.

[0038] Preferably, the step of determining the characteristic electricity consumption recorded by the smart meter in the next time period based on the recorded data includes:

[0039] When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, the time period in the historical time period that is the same as the characteristic temperature DW of the next time period, as well as the time period in the next time period where the maximum value GW and minimum value LW of several temperatures are the same, is marked as the reference time period of the current smart meter in the next time period.

[0040] When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, if there is a holiday in the next time period, the time period in the historical time period that contains the current holiday will be marked as the reference time period for the current smart meter in the next time period; if there is no holiday in the next time period, the time period in the historical time period that does not contain a holiday will be marked as the reference time period for the current smart meter in the next time period.

[0041] When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the time period with the same planned capacity in the historical time period and the next time period is marked as the reference time period for the current smart meter in the next time period.

[0042] The average electricity consumption of the current smart meter in each reference time period in the next time period is marked as the reference electricity consumption. Based on the reference electricity consumption, the characteristic electricity consumption TY recorded by the current smart meter in the next time period is determined; where i is the reference electricity consumption number, and the value range of i is [1,n], and n is the maximum value of the reference electricity consumption number;

[0043] The characteristic electricity consumption TY satisfies the following formula:

[0044] ;

[0045] Where TS is the number of days in the next time period, Mode() is the mode function, and max() is the maximum value function.

[0046] Preferably, the step of adjusting the characteristic electricity consumption to obtain the expected electricity consumption of the managed area in the next time period includes:

[0047] When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, extract the residential electricity consumption impact factor MZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the residential electricity consumption impact factor MZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period.

[0048] When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, extract the commercial electricity consumption impact factor SZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the commercial electricity consumption impact factor SZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period.

[0049] When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the industrial electricity consumption impact factor GZ and the characteristic electricity consumption TY of the current smart meter in the next time period are extracted. Based on the formula YD=TY×GZ / BGZ, the expected electricity consumption YD of the current smart meter in the next time period is obtained; where BGZ is the standard industrial electricity consumption impact factor.

[0050] The estimated electricity consumption of the smart meters in each management area is summed to obtain the estimated electricity consumption of the corresponding management area.

[0051] Preferably, determining the grid power supply for the next time period and the energy storage capacity for the current time period based on the expected electricity consumption includes:

[0052] Obtain the total service area of ​​the power supply company, and sum the estimated electricity consumption of each management area in the total service area to obtain the power grid supply of the total service area of ​​the power supply company;

[0053] Extract the estimated electricity consumption YD of the management area in the next time period. If the estimated electricity consumption YD in the next time period does not exceed the grid supply threshold GY, no operation is performed.

[0054] A power rationing notice will be issued when the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period also exceeds the grid supply threshold GY.

[0055] When the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period does not exceed the grid supply threshold GY, the difference YZ is recorded as the estimated electricity consumption YD for the next time period minus the grid supply threshold GY, and the difference DZ is recorded as the grid supply threshold GY minus the estimated electricity consumption for the current time period. It is then determined whether the difference YZ is greater than the difference DZ. If yes, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=DZ / DT. If no, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=YZ / DT. Where DT is the duration of the current time period.

[0056] Preferably, the step of adjusting the energy storage power supply in real time according to the grid power supply in the next time period includes:

[0057] When the power supply to the grid exceeds the grid load within a certain period of time, the energy storage system provides auxiliary power to the managed area.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] 1. This invention divides time periods and power supply companies into several management areas; sequentially acquires target data for each time period within the management area and recorded data from each smart meter; when the time reaches the first point of the current time period, it determines the residential electricity consumption impact factor based on the temperature and humidity of the next time period; it determines the commercial electricity consumption impact factor for each shopping mall based on the number of holidays in the next time period; it determines the industrial electricity consumption impact factor for each factory based on planned production capacity; it determines the characteristic electricity consumption recorded by smart meters in the next time period based on the recorded data; it adjusts the characteristic electricity consumption based on environmental electricity consumption impact factors, commercial electricity consumption impact factors, or industrial electricity consumption impact factors to obtain the expected electricity consumption of the management area in the next time period; it determines the grid power supply for the next time period and the energy storage capacity for the current time period based on the expected electricity consumption; and it adjusts the energy storage power supply in real time according to the grid power supply in the next time period. This solves the technical problems in power resource scheduling, such as the difficulty in adaptively scheduling power according to the regional electricity consumption characteristics and the difficulty in appropriately supplying power to the region according to the "grid + energy storage" dual power supply mode. This invention can solve the problems of inaccurate prediction and uneven resource allocation in traditional power scheduling, and improve the efficiency and stability of grid operation.

[0060] 2. This invention significantly improves the prediction accuracy and applicability of residential electricity consumption influencing factors through multi-dimensional feature extraction, piecewise logic design, nonlinear coupling modeling, and a human-data dual-driven strategy. This improvement is not only reflected in technical aspects, such as exponential correction terms and percentile feature extraction, but also in the systematic modeling of environmental physical characteristics, human comfort, and electricity consumption behavior, providing a practical theoretical framework for smart energy management. Compared to traditional methods, this invention offers greater flexibility, interpretability, and scenario adaptability, making it particularly suitable for electricity demand forecasting and resource allocation optimization under complex climatic conditions. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a schematic diagram of the operation steps of the present invention;

[0063] Figure 2 This is a schematic diagram illustrating the operational steps of dividing time periods and management areas according to the present invention;

[0064] Figure 3 This is a schematic diagram illustrating the operational steps for obtaining the industrial electricity impact factor according to the present invention. Detailed Implementation

[0065] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] Please see Figure 1 The first aspect of this invention provides an intelligent power distribution network resource scheduling and real-time management method, comprising:

[0067] Divide time periods and power supply companies into several management areas;

[0068] The system sequentially acquires target data for each time period within the managed area, as well as recorded data from each smart meter. The target data includes temperature, humidity, number of holidays, and planned production capacity for each factory. The recorded data includes electricity consumption type and electricity consumption at each time point.

[0069] When the time reaches the first point of the current time period, the impact factors on residential electricity consumption are determined based on the temperature and humidity of the next time period.

[0070] The impact factors on commercial electricity consumption of each shopping mall are determined based on the number of holiday days in the next time period.

[0071] The industrial electricity consumption impact factors for each factory are determined based on planned production capacity;

[0072] Based on the recorded data, determine the characteristic electricity consumption recorded by the smart meter in the next time period;

[0073] The expected electricity consumption of the management area in the next time period is obtained by adjusting the characteristic electricity consumption based on environmental electricity consumption impact factors, commercial electricity consumption impact factors, or industrial electricity consumption impact factors.

[0074] Based on the projected electricity consumption, the grid supply for the next time period and the energy storage capacity for the current time period are determined, and the energy storage supply is adjusted in real time according to the grid supply in the next time period.

[0075] Please see Figure 2 This application defines time periods and several management areas of the power supply company, including:

[0076] The total area for obtaining services from the power supply company is divided into separate management areas for individual factories, shopping malls, or residential communities within the total area; areas within the total area that are not divided into management areas are manually planned into several management areas.

[0077] When the first day of each month arrives, the total energy storage capacity ZD of the previous month in the total region is obtained; when the total energy storage capacity ZD is less than the storage capacity threshold CZ, the month is divided into several time periods according to the standard duration BC; when the total energy storage capacity ZD is not less than the storage capacity threshold CZ, the formula DC= BC×ρ×CZ / ZD The dynamic duration DC is obtained, and the month is divided into several time periods according to the dynamic duration DC; among them, the storage power threshold CZ and the standard duration BC are both manually set. ρ is the floor sign; ρ is the scaling factor, and the value of ρ ranges from (0,1).

[0078] It should be noted that the areas within the total area that are not designated as management areas are manually planned into several management areas, and this planning is done manually according to a fixed area; the fixed area is determined based on experience.

[0079] It should be noted that the stored electricity threshold CZ is obtained manually based on historical electricity consumption analysis within the total service area of ​​the power supply company, and the stored electricity threshold CZ is directly proportional to historical electricity consumption.

[0080] It should be noted that the standard duration BC can be 3 days, 4 days, 5 days, or 6 days, etc.

[0081] In this application, target data for each time period within the management area and recorded data from each smart meter are sequentially acquired, including:

[0082] Extract each management area sequentially, and obtain several temperatures and humidity levels for each time period within the management area through the weather forecast platform;

[0083] The database retrieves the number of holidays this month and the planned production capacity of each factory within each time period; smart meters retrieve the electricity consumption types and electricity consumption at each point in time within the managed area; the electricity consumption types include residential electricity, commercial electricity, and industrial electricity.

[0084] In this application, the impact factors on residential electricity consumption are determined based on the temperature and humidity of the next time period, including:

[0085] The target percentiles of several temperatures within each time period are marked as the characteristic temperature DW of the current time period, and the target percentiles of several humidity levels within each time period are marked as the characteristic humidity DS of the current time period; wherein, the percentiles in the target percentiles are obtained by manual setting.

[0086] Extract the characteristic temperature DW for the next time period, as well as the maximum value GW and minimum value LW of several temperatures within the next time period; when the characteristic temperature DW does not exceed the suitable temperature range, the residential electricity consumption impact factor is set to the standard electricity consumption impact factor BY; whereby the suitable temperature range is obtained artificially based on the human body's adaptation to various temperatures.

[0087] When the characteristic temperature DW is greater than the maximum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the maximum value GW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula:

[0088] ;

[0089] Where ZW is the midpoint of the suitable temperature range, and BS is the artificially set standard suitable humidity; and All of these are manually set proportional adjustment coefficients, and , ; The amplitude adjustment coefficient is set manually, and The value range is [0,1];

[0090] When the characteristic temperature DW is less than the minimum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the minimum value LW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula:

[0091] ;

[0092] in, and All of these are manually set proportional adjustment coefficients, and , .

[0093] It is worth noting that this method significantly improves the prediction accuracy and applicability of residential electricity consumption influencing factors through multi-dimensional feature extraction, piecewise logic design, nonlinear coupling modeling, and a dual-driven strategy of human and data. This improvement is not only reflected in technical aspects, such as exponential correction terms and percentile feature extraction, but also in the systematic modeling of environmental physical characteristics, human comfort, and electricity consumption behavior, providing a practical theoretical framework for smart energy management. Compared to traditional methods, this invention offers greater flexibility, interpretability, and scenario adaptability, making it particularly suitable for electricity demand forecasting and resource allocation optimization under complex climatic conditions.

[0094] It is worth noting that traditional electricity consumption forecasting models often rely on single variables such as temperature or humidity, while this method captures the impact of the environment on residential electricity consumption more comprehensively through multidimensional feature extraction and dynamic threshold setting. For example, the characteristic temperature (DW) is based on the target percentile, such as the 75th percentile, rather than the mean, which can more accurately reflect the impact of extreme weather on electricity consumption and avoid the mean masking the significant impact of local high or low temperatures on air conditioning or heating equipment.

[0095] It is worth noting that this invention links the physical environment with electricity consumption behavior by introducing segmented processing logic and parameterized formulas. For example, when the characteristic temperature DW is within a suitable range, the standard influence factor BY is directly used to simplify the calculation; when DW exceeds the range, an exponential function is used... Dynamic adjustments allow for the data-driven representation of the potential impact of humidity on temperature, improving the accuracy of the residential electricity consumption impact factor MZ.

[0096] It should be noted that, in this application, the target percentile is a value at a specific percentile among several temperatures or several humidity levels. If several temperatures are sorted in ascending order, and the manually set percentile is 75%, then the data at the 75th position of the several temperatures is the target percentile of the several temperatures. If there is no data at the 75th position among several temperatures, then the data closest to the 75th position is taken as the target percentile of the several temperatures.

[0097] It should be noted that the proportional adjustment coefficient Because: What is being multiplied is the characteristic temperature DW of the next time period. The multiplier is the maximum value GW of several temperatures within the next time period; because the characteristic temperature DW is more stable than the maximum temperature GW, and will not cause anomalies in subsequent data analysis due to excessively large extreme values, the proportional adjustment coefficient set in this invention is... ;

[0098] Similarly, the proportional adjustment coefficient Because: What is being multiplied is the characteristic temperature DW of the next time period. The multiplier is the minimum value LW of several temperatures within the next time period; because the characteristic temperature DW is more stable than the minimum temperature LW, and will not cause anomalies in subsequent data analysis due to excessively large extreme values, the proportional adjustment coefficient set in this invention... .

[0099] It should be noted that a suitable temperature range means that most people do not need to turn on the air conditioner, and the value can be [5℃, 30℃].

[0100] It should be noted that the standard suitable humidity (BS) is determined by human analysis of human adaptation to various humidity levels, and the standard suitable humidity (BS) can be set to 45%.

[0101] It should be noted that the amplitude adjustment coefficient It is set based on the humidity variation range of the current managed area, and the range adjustment coefficient is... It is inversely proportional to the magnitude of humidity change; the greater the magnitude of humidity change, the stronger the ability of the citizens in the current management area to adapt to complex humidity environment, resulting in less impact of humidity on citizens, and consequently, a lower degree of use of air conditioning or electric heating equipment.

[0102] In this application, the commercial electricity consumption impact factor for each shopping mall is determined based on the number of holiday days in the next time period, including:

[0103] Extract the number of holiday days RT in the next time period, the total number of days ZT in the next time period, and the average customer flow PL of the shopping mall during the current holiday in the historical data;

[0104] The commercial electricity consumption impact factor SZ for the current commercial electricity consumption area in the next time period is determined based on the number of holiday days RT, the total number of days ZT, and the average passenger flow PL; the commercial electricity consumption impact factor SZ satisfies the following formula:

[0105] ;

[0106] BPL is a manually set standard passenger flow. The ratio adjustment factor is set manually, and The value range is [0, 2].

[0107] It should be noted that the formula for obtaining the commercial electricity impact factor SZ in this invention has the following characteristics:

[0108] Smoothness property of logarithmic functions: and The product is logarithmically processed to effectively suppress the interference of extreme values. For example, when At that time, ln(10) = 2.3, which is far lower than the 10-fold effect of linear growth, thus avoiding the excessive amplification of the holiday effect;

[0109] Adaptive adjustment of parameters: by 0≤ With an adjustable range of ≤2, personalized configurations can be achieved for different business formats; shopping malls primarily serving young people can be set up with... =1.2 Enhance sensitivity to holidays, while shopping malls primarily serving the elderly can set up =0.8 reduces volatility;

[0110] Benchmark correction mechanism: in the formula The standardized processing makes the customer flow data of shopping malls of different sizes comparable, avoiding model bias caused by differences in size.

[0111] Please see Figure 3 In this application, the industrial electricity consumption impact factors for each factory are determined based on planned production capacity, including:

[0112] Extract the factory's planned capacity CN for the next time period, and the completion rate of the factory's planned capacity in each time period from historical data; integrate the completion rates of planned capacity in each time period into a capacity completion rate group, and obtain the variance of the completion rate in the capacity completion rate group; determine whether the variance of the capacity completion rate group is less than the defined variance; if yes, calculate the average of the completion rates in the capacity completion rate group to obtain the current factory's characteristic completion rate TL; if no, remove the completion rate in the capacity completion rate group that differs the most from the mode of the completion rate, and re-determine the variance until the variance of the capacity completion rate group is less than the defined variance, then calculate the average of the remaining completion rates in the capacity completion rate group to obtain the current factory's characteristic completion rate TL; the defined variance is obtained manually.

[0113] Multiply the planned capacity CN by the characteristic completion rate TL to obtain the industrial electricity consumption impact factor GZ of the current factory in the next time period.

[0114] It is worth noting that this invention integrates the planned capacity completion rate of a factory over multiple time periods into a completion rate group, comprehensively reflecting the factory's production stability. By judging whether the variance is less than a manually set defined variance, outliers are dynamically eliminated, such as extreme completion rates caused by sudden failures or special orders, ensuring that the final calculated feature completion rate is closer to the factory's normal production status. When the variance does not meet the standard, the completion rate with the largest difference from the mode, i.e., the data point that deviates most from the mainstream production level, is removed to gradually approach the stable dataset, avoiding interference from a single outlier. Compared with traditional methods, this invention can more accurately reflect the actual capacity fluctuation pattern of a factory, and is especially suitable for manufacturing scenarios with large capacity fluctuations, such as companies with seasonal production or frequent equipment maintenance, reducing the deviation in electricity consumption forecasting caused by abnormal data.

[0115] It should be noted that this invention combines planned production capacity with the dynamic correction results of historical completion rates to form a dual calibration mechanism. For example:

[0116] If a factory's historical completion rate is stable and its total electricity consumption (TL) is close to 1, it indicates strong production capacity execution capability, and electricity consumption can be directly estimated based on planned production capacity. If the completion rate fluctuates greatly, TL will decrease due to the removal of outliers, reflecting that actual electricity consumption may be lower than planned production capacity. Compared with a single indicator, such as using only historical averages, this method captures the factory's production capacity execution capability and electricity consumption behavior patterns more comprehensively through multi-dimensional data fusion, providing a more refined basis for energy management decisions.

[0117] It should be noted that the planned capacity completion rate for each time period is: the capacity completed by the factory in each time period divided by the planned capacity.

[0118] In this application, the characteristic electricity consumption recorded by the smart meter in the next time period is determined based on the recorded data, including:

[0119] When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, the time period in the historical time period that is the same as the characteristic temperature DW of the next time period, as well as the time period in the next time period where the maximum value GW and minimum value LW of several temperatures are the same, is marked as the reference time period of the current smart meter in the next time period.

[0120] When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, if there is a holiday in the next time period, the time period in the historical time period that contains the current holiday will be marked as the reference time period for the current smart meter in the next time period; if there is no holiday in the next time period, the time period in the historical time period that does not contain a holiday will be marked as the reference time period for the current smart meter in the next time period.

[0121] When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the time period with the same planned capacity in the historical time period and the next time period is marked as the reference time period for the current smart meter in the next time period.

[0122] The average electricity consumption of the current smart meter in each reference time period in the next time period is marked as the reference electricity consumption. Based on the reference electricity consumption, the characteristic electricity consumption TY recorded by the current smart meter in the next time period is determined; where i is the reference electricity consumption number, and the value range of i is [1,n], and n is the maximum value of the reference electricity consumption number;

[0123] The characteristic electricity consumption TY satisfies the following formula:

[0124] ;

[0125] Where TS is the number of days in the next time period, Mode() is the mode function, and max() is the maximum value function.

[0126] It should be noted that the average electricity consumption is the total electricity consumption over the reference period divided by the number of days.

[0127] It should be noted that this invention, by combining multi-dimensional statistics, not only preserves trend information but also takes into account extreme values ​​and typical patterns, significantly improving the comprehensiveness of prediction. For example, in industrial scenarios, if electricity consumption suddenly increases due to equipment maintenance during a certain period, the maximum value can effectively reflect this anomaly, while the average value can balance the long-term trend.

[0128] In this application, the predicted electricity consumption of the managed area in the next time period is obtained by adjusting the characteristic electricity consumption, including:

[0129] When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, extract the residential electricity consumption impact factor MZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the residential electricity consumption impact factor MZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period.

[0130] When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, extract the commercial electricity consumption impact factor SZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the commercial electricity consumption impact factor SZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period.

[0131] When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the industrial electricity consumption impact factor GZ and the characteristic electricity consumption TY of the current smart meter in the next time period are extracted. Based on the formula YD=TY×GZ / BGZ, the expected electricity consumption YD of the current smart meter in the next time period is obtained; where BGZ is the standard industrial electricity consumption impact factor.

[0132] The estimated electricity consumption of the smart meters in each management area is summed to obtain the estimated electricity consumption of the corresponding management area.

[0133] In this application, the grid power supply for the next time period and the energy storage capacity for the current time period are determined based on the projected electricity consumption, including:

[0134] Obtain the total service area of ​​the power supply company, and sum the estimated electricity consumption of each management area in the total service area to obtain the power grid supply of the total service area of ​​the power supply company;

[0135] Extract the estimated electricity consumption YD of the management area in the next time period. If the estimated electricity consumption YD in the next time period does not exceed the grid supply threshold GY, no operation is performed.

[0136] A power rationing notice will be issued when the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period also exceeds the grid supply threshold GY.

[0137] When the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period does not exceed the grid supply threshold GY, the difference YZ is recorded as the estimated electricity consumption YD for the next time period minus the grid supply threshold GY, and the difference DZ is recorded as the grid supply threshold GY minus the estimated electricity consumption for the current time period. It is then determined whether the difference YZ is greater than the difference DZ. If yes, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=DZ / DT. If no, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=YZ / DT. Where DT is the duration of the current time period.

[0138] It is worth noting that this step achieves dynamic coordination between grid supply and energy storage systems by real-time monitoring and prediction of the relationship between electricity demand and grid supply thresholds at different time periods. Traditional grid dispatching usually relies on static thresholds or fixed allocation strategies, while this solution can more accurately match supply and demand through scenario-based differentiated processing. For example, when YD exceeds GY but current electricity consumption is not exceeded, the system flexibly adjusts the charging strategy of the energy storage system by calculating the difference YZ and the difference DZ, avoiding "one-size-fits-all" power rationing measures, thereby reducing energy waste and the risk of power outages for users. This dynamic adjustment mechanism significantly improves the flexibility of the grid and energy utilization efficiency.

[0139] In this application, the energy storage power supply is adjusted in real time according to the grid power supply in the next time period, including:

[0140] When the power supply to the grid exceeds the grid load within a certain period of time, the energy storage system provides auxiliary power to the managed area.

[0141] It should be noted that auxiliary power supply refers to a power supply method that is mainly based on the power grid and supplemented by the energy storage system. The power grid only supplies electricity that does not exceed the grid load, while the energy storage system supplies the additional electricity demand that exceeds the grid load.

[0142] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0143] Working principle of the invention:

[0144] The present invention first divides time periods and several management areas of power supply companies; then sequentially obtains the temperature, humidity, number of holidays and the planned production capacity of each factory in each time period within the management area, as well as the electricity consumption type and electricity consumption at each time point of each smart meter.

[0145] Then, when the time reaches the first point in the current time period, the following operations are performed:

[0146] The following factors determine the impact factors on residential electricity consumption based on temperature and humidity in the next time period: the impact factors on commercial electricity consumption in shopping malls based on the number of holiday days in the next time period; the impact factors on industrial electricity consumption in factories based on planned production capacity; the characteristic electricity consumption recorded by smart meters in the next time period based on recorded data; the expected electricity consumption in the management area in the next time period by adjusting the characteristic electricity consumption based on environmental electricity consumption impact factors, commercial electricity consumption impact factors, or industrial electricity consumption impact factors; the grid power supply in the next time period and the energy storage capacity in the current time period based on the expected electricity consumption; and the energy storage power supply is adjusted in real time according to the grid power supply in the next time period.

[0147] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for intelligent power distribution network resource scheduling and real-time management, characterized in that, include: Divide time periods and power supply companies into several management areas; The system sequentially acquires target data for each time period within the managed area, as well as recorded data from each smart meter. The recorded data includes electricity consumption type and electricity consumption at each time point. When the time reaches the first point of the current time period, the impact factors on residential electricity consumption are determined based on the temperature and humidity of the next time period. The impact factors on commercial electricity consumption of each shopping mall are determined based on the number of holiday days in the next time period. The industrial electricity consumption impact factors for each factory are determined based on planned production capacity; Based on the recorded data, determine the characteristic electricity consumption recorded by the smart meter in the next time period; The expected electricity consumption of the management area in the next time period is obtained by adjusting the characteristic electricity consumption based on environmental electricity consumption impact factors, commercial electricity consumption impact factors, or industrial electricity consumption impact factors. Based on the expected electricity consumption, determine the grid power supply for the next time period and the energy storage capacity for the current time period, and adjust the energy storage power supply in real time according to the grid power supply in the next time period. The defined time periods and several management areas of the power supply company include: The total area served by the power supply company is obtained, and individual factories, shopping malls, or residential communities within the total area are divided into independent management areas; areas within the total area that are not divided into management areas are manually planned into several management areas. When the first day of each month arrives, the total energy storage capacity ZD of the previous month in the total region is obtained; when the total energy storage capacity ZD is less than the storage capacity threshold CZ, the month is divided into several time periods according to the standard duration BC; when the total energy storage capacity ZD is not less than the storage capacity threshold CZ, the formula DC= BC×ρ×CZ / ZD Obtain the dynamic duration DC, and divide this month into several time periods according to the dynamic duration DC; among them, ρ is the floor sign; ρ is the scaling factor, and the value of ρ ranges from (0,1).

2. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The determination of residential electricity consumption impact factors based on temperature and humidity in the next time period includes: The target percentiles of several temperatures within each time period are marked as the characteristic temperature DW of the current time period, and the target percentiles of several humidity levels within each time period are marked as the characteristic humidity DS of the current time period. Extract the characteristic temperature DW for the next time period, as well as the maximum value GW and minimum value LW of several temperatures within the next time period; when the characteristic temperature DW does not exceed the suitable temperature range, the residential electricity consumption impact factor is set to the standard electricity consumption impact factor BY. When the characteristic temperature DW is greater than the maximum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the maximum value GW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula: ； Where ZW is the midpoint of the suitable temperature range, and BS is the standard suitable humidity; and All are proportional adjustment coefficients, and , ; This is the amplitude adjustment coefficient, and The value range is [0,1]; When the characteristic temperature DW is less than the minimum value of the suitable temperature range, the residential electricity consumption impact factor MZ is determined based on the characteristic temperature DW, the minimum value LW, and the characteristic humidity DS; the residential electricity consumption impact factor MZ satisfies the following formula: ； in, and All are proportional adjustment coefficients, and , .

3. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The determination of the commercial electricity consumption impact factors for each shopping mall based on the number of holiday days in the next time period includes: Extract the number of holiday days RT in the next time period, the total number of days ZT in the next time period, and the average customer flow PL of the shopping mall during the current holiday in the historical data; Based on the number of holiday days RT, the total number of days ZT, and the average passenger flow PL, the commercial electricity consumption impact factor SZ for the current commercial electricity consumption area in the next time period is determined; the commercial electricity consumption impact factor SZ satisfies the following formula: ； BPL represents the standard passenger flow. It is a proportional adjustment factor, and The value range is [0, 2].

4. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The determination of industrial electricity consumption impact factors for each factory based on planned production capacity includes: Extract the factory's planned capacity CN for the next time period, and the completion rate of the factory's planned capacity in each time period from historical data; integrate the completion rates of the planned capacity in each time period into a capacity completion rate group, and obtain the variance of the completion rate in the capacity completion rate group; determine whether the variance of the capacity completion rate group is less than the defined variance; if yes, calculate the average of the completion rates in the capacity completion rate group to obtain the characteristic completion rate TL of the current factory; if no, remove the completion rate in the capacity completion rate group that differs the most from the mode of the completion rate, and re-determine the variance until the variance of the capacity completion rate group is less than the defined variance, and calculate the average of the remaining completion rates in the capacity completion rate group to obtain the characteristic completion rate TL of the current factory. Multiply the planned capacity CN by the characteristic completion rate TL to obtain the industrial electricity consumption impact factor GZ of the current factory in the next time period.

5. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The process of determining the characteristic electricity consumption recorded by the smart meter in the next time period based on the recorded data includes: When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, the time period in the historical time period that is the same as the characteristic temperature DW of the next time period, as well as the time period in the next time period where the maximum value GW and minimum value LW of several temperatures are the same, is marked as the reference time period of the current smart meter in the next time period. When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, if there is a holiday in the next time period, the time period in the historical time period that contains the current holiday will be marked as the reference time period for the current smart meter in the next time period; if there is no holiday in the next time period, the time period in the historical time period that does not contain a holiday will be marked as the reference time period for the current smart meter in the next time period. When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the time period with the same planned capacity in the historical time period and the next time period is marked as the reference time period for the current smart meter in the next time period. The average electricity consumption of the current smart meter in each reference time period in the next time period is marked as the reference electricity consumption. Based on the reference electricity consumption, the characteristic electricity consumption TY recorded by the current smart meter in the next time period is determined; where i is the reference electricity consumption number, and the value range of i is [1,n], and n is the maximum value of the reference electricity consumption number; The characteristic electricity consumption TY satisfies the following formula: ； Where TS is the number of days in the next time period, Mode() is the mode function, and max() is the maximum value function.

6. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The process of adjusting the characteristic electricity consumption to obtain the expected electricity consumption of the managed area in the next time period includes: When the electricity consumption type of the user corresponding to the smart meter is residential electricity consumption, extract the residential electricity consumption impact factor MZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the residential electricity consumption impact factor MZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period. When the electricity consumption type of the user corresponding to the smart meter is commercial electricity consumption, extract the commercial electricity consumption impact factor SZ and the characteristic electricity consumption TY recorded by the current smart meter in the next time period, and multiply the commercial electricity consumption impact factor SZ by the characteristic electricity consumption TY to obtain the expected electricity consumption of the current smart meter in the next time period. When the electricity consumption type of the user corresponding to the smart meter is industrial electricity consumption, the industrial electricity consumption impact factor GZ and the characteristic electricity consumption TY of the current smart meter in the next time period are extracted. Based on the formula YD=TY×GZ / BGZ, the expected electricity consumption YD of the current smart meter in the next time period is obtained; where BGZ is the standard industrial electricity consumption impact factor. The estimated electricity consumption of the smart meters in each management area is summed to obtain the estimated electricity consumption of the corresponding management area.

7. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The process of determining the grid supply for the next time period and the energy storage capacity for the current time period based on the projected electricity consumption includes: The total service area of ​​the power supply company is obtained, and the expected electricity consumption of each management area in the total area is summed to obtain the power supply of the power grid in the total service area of ​​the power supply company. Among them, the management area includes a single factory, a single shopping mall or a single residential community in the total area, and the areas in the total area that are not divided into management areas are manually planned into several management areas. Extract the estimated electricity consumption YD of the management area in the next time period. If the estimated electricity consumption YD in the next time period does not exceed the grid supply threshold GY, no operation is performed. A power rationing notice will be issued when the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period also exceeds the grid supply threshold GY. When the estimated electricity consumption YD for the next time period exceeds the grid supply threshold GY and the estimated electricity consumption for the current time period does not exceed the grid supply threshold GY, the difference YZ is recorded as the estimated electricity consumption YD for the next time period minus the grid supply threshold GY, and the difference DZ is recorded as the grid supply threshold GY minus the estimated electricity consumption for the current time period. It is then determined whether the difference YZ is greater than the difference DZ. If yes, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=DZ / DT. If no, the daily energy storage capacity CD for charging the energy storage system in the current time period is obtained based on the formula CD=YZ / DT. Where DT is the duration of the current time period.

8. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The real-time adjustment of energy storage power supply based on grid power supply in the next time period includes: When the power supply to the grid exceeds the grid load within a certain period of time, the energy storage system provides auxiliary power to the managed area.

9. The intelligent power distribution network resource scheduling and real-time management method according to claim 1, characterized in that, The process of sequentially acquiring target data for each time period within the management area and recorded data from each smart meter includes: Each management area is extracted sequentially, and several temperatures and humidity levels for each time period within the management area are obtained through a weather forecast platform; The database is used to obtain the number of holidays this month and the planned production capacity of each factory in each time period; the smart meters are used to obtain the electricity consumption type and electricity consumption at each time point in the managed area; the electricity consumption type includes residential electricity, commercial electricity and industrial electricity.

Images