Declared electric quantity prediction method and system based on correlation

Abstract

The invention belongs to the technical field of energy, and particularly relates to a correlation-based declared electric quantity prediction method and system. The method comprises the following steps: determining a daily mean value and a monthly value of electric quantity of a current month; determining an electric quantity predicted value according to the daily mean value and the monthly value; and predicting the total power consumption according to the electric quantity predicted value. According to the method, the daily mean value and the monthly value of the electric quantity of the current month are determined, so that the electric quantity predicted value is determined, the total power consumption is predicted according to the electric quantity predicted value, the electric quantity is predicted by using the correlation coefficient, the year-on-year coefficient and the link-on-year coefficient when the monthly value is determined, and the method is more accurate than single mathematical model prediction and expert experience prediction.

Description

Technical Field This invention belongs to the field of energy technology, and specifically relates to a correlation-based method and system for predicting reported electricity volume. Background Technology

[0001] Electricity forecasting refers to estimating the patterns of electricity consumption changes based on historical electricity data and relevant economic and meteorological factors, thereby predicting the load consumption of the power system over a future period. Demand forecasting, with monthly maximum electricity load as the core indicator, is a component guiding electricity users' demand declarations and an important decision-making reference for assessing their production and operation. It involves understanding the year-on-year and month-on-month growth of various economic and electricity indicators, the development of economic production indicators, and the level of electricity consumption activity. In addition to understanding the current characteristic values ​​of various indicators, it is also necessary to understand their development trends to provide decision-making references for demand declarations.

[0002] Currently, commonly used electricity consumption forecasting methods mainly include mathematical model-based forecasting methods and expert experience-based forecasting methods. The disadvantage of expert experience-based forecasting methods is that they rely on the judgment of expert groups, which makes them highly subjective and results in a high degree of randomness. Mathematical model-based forecasting methods can overcome the influence of subjective factors and are based on mathematical formulas, but none of them can simulate the many factors that affect electricity consumption, thus affecting the accuracy of the forecast. Summary of the Invention

[0003] To address the above problems, this invention provides a correlation-based method for predicting reported electricity consumption, the method comprising: Determine the daily average and monthly electricity consumption for the current month; The predicted electricity consumption value is determined based on the daily average and monthly values. The total electricity consumption is predicted based on the predicted electricity consumption value.

[0004] Furthermore, determining the average daily electricity consumption for the current month includes: The weekly year-on-year coefficients are weighted and summed using the weekly average values ​​to obtain the summation result; The calculation deviation rate and adjustment coefficient are preset, the summation result is divided by the calculation accuracy rate, and the daily average value is determined by multiplying the quotient result by the adjustment coefficient. The calculation accuracy rate is 1 minus the calculation deviation rate.

[0005] Furthermore, determining the monthly value of the current month's electricity consumption includes: Determine the annual correlation coefficient between the current year and a reference year; the reference year is not the current year. Determine whether the annual correlation coefficient is greater than a preset coefficient, and determine the monthly value based on the determination result.

[0006] Furthermore, determining the monthly value based on the judgment result includes: If the annual correlation coefficient is greater than the preset coefficient, then the year-on-year coefficient of the current month's electricity consumption is determined, and the monthly value is determined based on the year-on-year coefficient, the annual correlation coefficient, and the actual electricity consumption of the previous month in the reference year. If the annual correlation coefficient is not greater than the preset coefficient, then the average year-on-year coefficient of the reference year is determined, and the monthly value is determined based on the actual electricity consumption of the previous month of the current year and the average year-on-year coefficient.

[0007] Furthermore, when the annual correlation coefficient is greater than a preset coefficient, the formula for calculating the monthly value is as follows: ; in, Indicates monthly value. This indicates the actual electricity consumption for the previous month of the reference year. This represents the year-on-year coefficient. This represents the annual correlation coefficient.

[0008] Furthermore, when the annual correlation coefficient is not greater than a preset coefficient, the formula for calculating the monthly value is as follows: ; in, Indicates monthly value. This indicates the actual electricity consumption in the previous month of the current year. This represents the average year-on-year growth rate.

[0009] Furthermore, the calculation formula for determining the electricity consumption forecast based on the daily average and monthly values ​​is as follows: ; in, This represents the predicted electricity consumption value. This represents the daily average. This represents the monthly value.

[0010] Furthermore, predicting the total electricity consumption based on the predicted electricity consumption value includes: The total electricity consumption is determined by multiplying the predicted electricity consumption value with the preset control coefficient and the deviation correction coefficient.

[0011] This invention also proposes a correlation-based forecasting system for reported electricity consumption, the system comprising: The first determining module is used to determine the daily average and monthly electricity consumption for the current month. The second determining module is used to determine the predicted electricity consumption value based on the daily average value and the monthly value; The prediction module is used to predict the total electricity consumption based on the predicted electricity consumption value.

[0012] Furthermore, the first determining module is used to determine the monthly value of the current month's electricity consumption, including: The first determining module is used to determine the annual correlation coefficient between the current year and the reference year; the reference year is not the current year; Determine whether the annual correlation coefficient is greater than a preset coefficient, and determine the monthly value based on the determination result.

[0013] The present invention has the following beneficial effects: This invention determines the electricity consumption forecast by identifying the daily average and monthly electricity consumption for the current month, and then predicts the total electricity consumption based on the forecast. When determining the monthly value, correlation coefficient, year-on-year coefficient, and month-on-month coefficient are used to predict the electricity consumption, which is more accurate than predictions based on a single mathematical model or expert experience.

[0014] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description and the drawings. Attached Figure Description

[0015] 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A diagram illustrating the correlation-based power forecasting method in an embodiment of the present invention is shown. Figure 2 This illustrates a flowchart of the monthly calculation process in an embodiment of the present invention. Figure 3 A diagram of a correlation-based electricity forecasting system is shown in an embodiment of the present invention. Detailed Implementation

[0017] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0018] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware units or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0019] The flowchart shown in the attached diagram is merely an illustrative example and does not necessarily include all steps. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0020] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0021] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or device that includes a series of steps or sub-modules is not necessarily limited to those steps or sub-modules that are explicitly listed, but may include other steps or sub-modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0022] like Figure 1 As shown, this invention proposes a correlation-based method for predicting reported electricity consumption, the method comprising: S1 determines the daily average and monthly electricity consumption for the current month; S2 determines the predicted electricity consumption value based on the daily average and monthly values; S3 predicts the total electricity consumption based on the predicted electricity consumption value.

[0023] Specifically, S1 determines the average daily electricity consumption for the current month, including: The weekly year-on-year coefficients are weighted and summed using the weekly average values ​​to obtain the summation result; The calculation deviation rate and adjustment coefficient are preset, the summation result is divided by the calculation accuracy rate, and the daily average value is determined by multiplying the quotient result by the adjustment coefficient. The calculation accuracy rate is 1 minus the calculation deviation rate.

[0024] Specifically, S1, which describes determining the monthly electricity consumption value for the current month, includes: Determine the annual correlation coefficient between the current year and a reference year; the reference year is not the current year. Determine whether the annual correlation coefficient is greater than a preset coefficient, and determine the monthly value based on the determination result.

[0025] Specifically, S1 describes determining the monthly value based on the judgment result, such as... Figure 2 As shown, it includes: If the annual correlation coefficient is greater than the preset coefficient Then determine the year-on-year coefficient for electricity consumption in the current month. According to the year-on-year coefficient The annual correlation coefficient The monthly value is determined by the actual electricity consumption of the previous month in the reference year. ; If the annual correlation coefficient If the coefficient is not greater than the preset coefficient, then the average year-on-year coefficient of the reference year is determined. The monthly value is determined based on the actual electricity consumption of the previous month in the current year and the average of the year-on-year comparison coefficient. .

[0026] In this embodiment, the preset coefficient is set to 0.7, but it is not fixed and can be modified according to actual needs.

[0027] Specifically, when the annual correlation coefficient is greater than the preset coefficient, the monthly value is calculated using the following formula: ; in, Indicates monthly value. This indicates the actual electricity consumption for the previous month of the reference year. This represents the year-on-year coefficient. This represents the annual correlation coefficient.

[0028] In this embodiment, the year-on-year coefficient This reflects changes over the same period. The calculation formula is as follows: Electricity consumption in month n of this year is compared to electricity consumption in month n of last year. ; Among them, the year-on-year coefficient The index range is [0.85, 1.2]; This indicates the electricity consumption in the nth month of this year; This represents the electricity consumption in the nth month of last year.

[0029] In this embodiment, the correlation coefficient This is a statistical indicator reflecting the relationship between variables, ranging from 1 to -1. 1 indicates a perfect linear correlation between the two variables, -1 indicates a perfect negative correlation, and 0 indicates no correlation. The closer the data is to 0, the weaker the correlation. The calculation formula is as follows: ; ; ; ; in, Represents covariance; The standard deviation of variable x; The standard deviation of the variable y; Represents the data points of variable x; Represents the data points of variable y; This represents the sample mean of variable x; This represents the sample mean of the variable y; This indicates the total amount of data.

[0030] Specifically, when the annual correlation coefficient is not greater than the preset coefficient, the monthly value is calculated using the following formula: ; in, Indicates monthly value. This indicates the actual electricity consumption in the previous month of the current year. This represents the average year-on-year growth rate.

[0031] In this embodiment, the month-on-month coefficient It reflects the changes between the current period and the previous period, and the current month's electricity consumption. Compared with last month's electricity consumption In contrast, the calculation formula is as follows: .

[0032] Specifically, S2 determines the predicted electricity consumption value based on the daily average and monthly values ​​using the following formula: ; in, This represents the predicted electricity consumption value. This represents the daily average. This represents the monthly value.

[0033] In this embodiment, the daily average value The calculation process is as follows: ; in, This is expressed as the average value of the first week of the previous month; This is expressed as the year-on-year coefficient for the first week of the previous month; This is expressed as an adjustment factor; This is expressed as the calculated deviation rate.

[0034] In this embodiment, if some weeks have fewer than 7 days, taking April 2025 as an example, the fifth week only has three days: the 28th, 29th, and 30th. That's the average of these three days.

[0035] Specifically, calculate the deviation rate. The calculation formula is as follows: ; in, This is expressed as actual electricity consumption. This is used to calculate the amount of electricity.

[0036] In this embodiment, if changes in the production plan are involved, the fluctuation coefficient must be considered; if subsequent statistical analysis is involved, the reporting deviation rate must be considered.

[0037] Specifically, S3 predicts the total electricity consumption based on the predicted electricity consumption value, including: The total electricity consumption is determined by multiplying the predicted electricity consumption value with the preset control coefficient and the deviation correction coefficient.

[0038] In this embodiment, the control coefficient is set to 0.995 and the deviation correction coefficient is set to 1.02. However, the above coefficients are not unique and can be adjusted according to the actual situation.

[0039] like Figure 3 As shown, the present invention also proposes a correlation-based forecasting system for electricity consumption, the system comprising: The first determining module 10 is used to determine the daily average and monthly electricity consumption for the current month; The second determining module 20 is used to determine the predicted electricity consumption value based on the daily average value and the monthly value; The prediction module 30 is used to predict the total electricity consumption based on the predicted electricity value.

[0040] Those skilled in the art should understand that, despite the detailed description of the present invention with reference to the foregoing embodiments, modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A correlation-based method for predicting reported electricity consumption, characterized in that, The method includes: Determine the daily average and monthly electricity consumption for the current month; The predicted electricity consumption value is determined based on the daily average and monthly values. The total electricity consumption is predicted based on the predicted electricity consumption value.

2. The correlation-based electricity forecasting method according to claim 1, characterized in that, Determining the daily average electricity consumption for the current month includes: The weekly year-on-year coefficients are weighted and summed using the weekly average values ​​to obtain the summation result; The calculation deviation rate and adjustment coefficient are preset, the summation result is divided by the calculation accuracy rate, and the daily average value is determined by multiplying the quotient result by the adjustment coefficient. The calculation accuracy rate is 1 minus the calculation deviation rate.

3. The correlation-based electricity forecasting method according to claim 1, characterized in that, Determining the monthly electricity consumption value for the current month includes: Determine the annual correlation coefficient between the current year and a reference year; the reference year is not the current year. Determine whether the annual correlation coefficient is greater than a preset coefficient, and determine the monthly value based on the determination result.

4. The correlation-based electricity forecasting method according to claim 3, characterized in that, The process of determining the monthly value based on the judgment result includes: If the annual correlation coefficient is greater than the preset coefficient, then the year-on-year coefficient of the current month's electricity consumption is determined, and the monthly value is determined based on the year-on-year coefficient, the annual correlation coefficient, and the actual electricity consumption of the previous month in the reference year. If the annual correlation coefficient is not greater than the preset coefficient, then the average year-on-year coefficient of the reference year is determined, and the monthly value is determined based on the actual electricity consumption of the previous month of the current year and the average year-on-year coefficient.

5. The correlation-based electricity forecasting method according to claim 4, characterized in that, When the annual correlation coefficient is greater than the preset coefficient, the monthly value is calculated using the following formula: ； in, Indicates monthly value. This indicates the actual electricity consumption for the previous month of the reference year. This represents the year-on-year coefficient. This represents the annual correlation coefficient.

6. The correlation-based electricity forecasting method according to claim 4, characterized in that, When the annual correlation coefficient is not greater than the preset coefficient, the formula for calculating the monthly value is as follows: ； in, Indicates monthly value. This indicates the actual electricity consumption in the previous month of the current year. This represents the average year-on-year growth rate.

7. The correlation-based electricity forecasting method according to claim 1, characterized in that, The calculation formula for determining the predicted electricity consumption value based on the daily average and monthly values ​​is as follows: ； in, This represents the predicted electricity consumption value. This represents the daily average. This represents the monthly value.

8. The correlation-based electricity forecasting method according to claim 1, characterized in that, Predicting total electricity consumption based on the predicted electricity consumption value includes: The total electricity consumption is determined by multiplying the predicted electricity consumption value with the preset control coefficient and the deviation correction coefficient.

9. A correlation-based electricity forecasting system, characterized in that, The system includes: The first determining module is used to determine the daily average and monthly electricity consumption for the current month. The second determining module is used to determine the predicted electricity consumption value based on the daily average value and the monthly value; The prediction module is used to predict the total electricity consumption based on the predicted electricity consumption value.

10. The correlation-based electricity forecasting system according to claim 9, characterized in that, The first determining module is used to determine the monthly electricity consumption value for the current month, including: The first determining module is used to determine the annual correlation coefficient between the current year and the reference year; the reference year is not the current year; Determine whether the annual correlation coefficient is greater than a preset coefficient, and determine the monthly value based on the determination result.

Images