Electrical load prediction method and device based on temperature and humidity index cumulative effect
By introducing the accumulated effect of temperature and humidity index, the problem of inaccurate prediction results of electricity loads in the prior art is solved, the accuracy of prediction of electricity loads in summer is improved, and a scientific basis for the reasonable scheduling of the power system is provided.
Patent Information
- Application Number
- CN202411107031.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-12-03
AI Technical Summary
When considering a single discrete meteorological indicator, the existing power load prediction methods cannot accurately reflect timing and seasonal differences, resulting in inaccurate prediction results of summer power load and lack of scientific scheduling basis.
The temperature and humidity index cumulative effect is introduced. By generating the accumulated effect value of the temperature and humidity index, combined with the meteorological load peak timing data, the relative change of the peak power load is calculated, and a more accurate prediction result of the electricity load is generated.
It improves the accuracy of peak prediction of electricity load, provides a scientific and effective basis for electricity load scheduling in summer, especially under high temperature and high humidity conditions, and enhances the safety and reliability of the power system.
Smart Images

Figure CN119070277A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power load forecasting, and in particular to a method and device for forecasting power load based on the cumulative effect of temperature and humidity index. Background Art
[0002] Accurate and efficient power load forecasting is the basis for the grid to reasonably arrange power generation plans, and is also a prerequisite for ensuring the safe and reliable operation of the power system. On the basis of the basic power load, changes in weather factors often cause large fluctuations in power load, especially in the summer in North China, where the temperature is high, the relative humidity is high, and the human comfort is poor, which often causes a sharp increase in air conditioning load, posing a great challenge to power dispatching. In related technologies, power load forecasting is usually based on discrete indicators of historical meteorological conditions, but there is a certain temporal correlation and seasonal difference between the indicators. Considering only a single discrete indicator will lead to inaccurate prediction results, resulting in a lack of reasonable and scientific basis for power load dispatching. Summary of the invention
[0003] One object of the present invention is to provide a method for predicting power load based on the cumulative effect of temperature and humidity index. On the basis of conventional meteorological elements, the cumulative effect of temperature and humidity index is introduced, and the influence of a unit change of the cumulative effect of temperature and humidity index on the meteorological load peak is calculated, so as to improve the accuracy of the prediction result of power load peak, thereby providing a scientific and effective basis for the prediction of power load in summer, especially the reasonable scheduling of power load under continuous high temperature and high humidity meteorological conditions. Another object of the present invention is to provide a power load prediction device based on the cumulative effect of temperature and humidity index. Another object of the present invention is to provide a computer readable medium. Another object of the present invention is to provide a computer device.
[0004] In order to achieve the above objectives, the present invention discloses, on one hand, a method for predicting power load based on the cumulative effect of temperature and humidity index, comprising:
[0005] Data is extracted based on the acquired historical power load peak time series data for a specified time period to generate basic power load time series data and meteorological load peak time series data;
[0006] Generate the cumulative effect value of the temperature and humidity index based on the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data;
[0007] According to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data, the relative change of the cumulative effect value to the power load peak time series data is generated;
[0008] The power load forecast result is generated based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak preliminary measurement results and random variables. The meteorological load peak preliminary measurement results are calculated based on the pre-constructed meteorological load peak preliminary measurement model.
[0009] Preferably, data extraction is performed based on the acquired historical power load peak time series data of the specified time period to generate basic power load time series data and meteorological load peak time series data, including:
[0010] Generate linear trend values based on historical power load peak time series data;
[0011] Generate basic power load time series data according to linear tendency value, preset basic constant term and time series;
[0012] Subtract the historical electricity load peak time series data from the basic electricity load time series data to generate the meteorological load peak time series data.
[0013] Preferably, the historical meteorological observation time series data includes average temperature and average relative humidity;
[0014] Based on the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data, the cumulative effect value of the temperature and humidity index is generated, including:
[0015] Generate a time series of temperature and humidity index based on the average temperature and average relative humidity;
[0016] The cumulative effect value of the temperature and humidity index is generated based on the temperature and humidity index time series, basic power load time series data and meteorological load peak time series data.
[0017] Preferably, the cumulative effect value of the temperature and humidity index is generated according to the temperature and humidity index time series, the basic power load time series data and the meteorological load peak time series data, including:
[0018] Generate meteorological time series variation of power load according to basic power load time series data and meteorological load peak time series data;
[0019] Based on the preset temperature and humidity index threshold, the meteorological time series variation of the power load is screened and the average value is calculated according to the temperature and humidity index time series to generate the meteorological average variation of the power load;
[0020] According to the time series of temperature and humidity index, determine the critical value of temperature and humidity index;
[0021] According to the critical value of the temperature and humidity index, the cumulative cycle statistics are performed according to the temperature and humidity index time series to generate the cumulative cycle value;
[0022] The cumulative effect value of the temperature and humidity index is generated according to the accumulated cycle value, the critical value of the temperature and humidity index and the current temperature and humidity index obtained.
[0023] Preferably, according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data, the relative change amount of the cumulative effect value to the power load peak time series data is generated, including:
[0024] According to the cumulative effect value of the temperature and humidity index, the relative risk of the cumulative effect value to the peak value of power load is generated;
[0025] Based on the relative risk and meteorological load peak time series data, the relative change of the cumulative effect value to the peak power load is generated.
[0026] Preferably, according to the cumulative effect value of the temperature and humidity index, the relative risk of the cumulative effect value to the peak value of the power load is generated, including:
[0027] Perform logarithmic curve fitting according to the preset expected value of power load and the cumulative effect value of temperature and humidity index to generate fitting coefficient;
[0028] Based on Poisson distribution, the relative risk of the cumulative effect value to the peak power load is generated according to the change of the fitting coefficient and the cumulative effect value of the temperature and humidity index.
[0029] Preferably, the relative change of the cumulative effect value to the peak power load is generated according to the relative risk degree and the meteorological load peak time series data, including:
[0030] According to the relative risk, the relative change rate of the cumulative effect value to the peak value of power load is generated;
[0031] The relative change rate of the cumulative effect value to the peak power load is multiplied by the meteorological load peak time series data to generate the relative change of the cumulative effect value to the peak power load.
[0032] Preferably, before generating the power load forecast result according to the relative change amount of the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement results and the random variables, the method further includes:
[0033] The correlation between the historical meteorological observation time series data and the meteorological load peak time series data was calculated to screen out significant meteorological factors.
[0034] Based on the multiple regression method, the meteorological load peak preliminary measurement model is generated according to the significant meteorological factors and partial regression coefficients.
[0035] The present invention also discloses a power load prediction device based on the cumulative effect of temperature and humidity index, comprising:
[0036] A data extraction unit, used to extract data based on the acquired historical power load peak time series data of a specified time period, and generate basic power load time series data and meteorological load peak time series data;
[0037] A cumulative effect generating unit, used to generate a cumulative effect value of a temperature and humidity index according to the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data;
[0038] A relative change amount generating unit is used to generate a relative change amount of the cumulative effect value to the peak time series data of the power load according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data;
[0039] The load forecasting unit is used to generate power load forecasting results based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak preliminary measurement results and random variables. The meteorological load peak preliminary measurement results are calculated based on the pre-built meteorological load peak preliminary measurement model.
[0040] Preferably, the data extraction unit is specifically used to generate a linear tendency value based on historical power load peak time series data; generate basic power load time series data based on the linear tendency value, a preset basic constant term and a time series; and subtract the historical power load peak time series data from the basic power load time series data to generate meteorological load peak time series data.
[0041] Preferably, the historical meteorological observation time series data includes average temperature and average relative humidity;
[0042] The cumulative effect generation unit is specifically used to generate a temperature and humidity index time series based on the average temperature and average relative humidity; and to generate a cumulative effect value of the temperature and humidity index based on the temperature and humidity index time series, basic power load time series data and meteorological load peak time series data.
[0043] Preferably, the cumulative effect generating unit is specifically used to generate the meteorological time series variation of the power load based on the basic power load time series data and the meteorological load peak time series data; based on the preset temperature and humidity index threshold, the meteorological time series variation of the power load is screened and the average value is calculated according to the temperature and humidity index time series to generate the meteorological average variation of the power load; according to the temperature and humidity index time series, the critical value of the influence of the temperature and humidity index is determined; according to the temperature and humidity index time series, the cumulative cycle statistics are performed according to the temperature and humidity index time series to generate the cumulative cycle value; according to the cumulative cycle value, the critical value of the influence of the temperature and humidity index and the current temperature and humidity index obtained, the cumulative effect value of the temperature and humidity index is generated.
[0044] Preferably, the relative change generating unit is specifically used to generate the relative risk of the cumulative effect value to the peak power load based on the cumulative effect value of the temperature and humidity index; and to generate the relative change of the cumulative effect value to the peak power load based on the relative risk and the meteorological load peak time series data.
[0045] Preferably, the relative change generation unit is specifically used to perform logarithmic curve fitting according to the preset expected value of power load and the cumulative effect value of the temperature and humidity index to generate a fitting coefficient; based on the Poisson distribution, the relative risk of the cumulative effect value to the peak value of power load is generated according to the change of the fitting coefficient and the cumulative effect value of the temperature and humidity index.
[0046] Preferably, the relative change generating unit is specifically used to generate the relative change rate of the cumulative effect value to the peak value of the power load according to the relative risk; multiply the relative change rate of the cumulative effect value to the peak value of the power load by the meteorological load peak time series data to generate the relative change of the cumulative effect value to the peak value of the power load.
[0047] Preferably, the device further comprises:
[0048] A correlation calculation unit is used to perform correlation calculation based on the historical meteorological observation time series data and the meteorological load peak time series data to screen out significant meteorological factors;
[0049] The modeling unit is used to generate a preliminary measurement model of the meteorological load peak based on the multiple regression method, according to significant meteorological factors and partial regression coefficients.
[0050] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.
[0051] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.
[0052] The present invention also discloses a computer program product, including a computer program / instruction, and the method described above is implemented when the computer program / instruction is executed by a processor.
[0053] The present invention extracts data based on the acquired historical power load peak time series data of the specified time period to generate basic power load time series data and meteorological load peak time series data; generates the cumulative effect value of the temperature and humidity index based on the acquired historical meteorological observation time series data, the basic power load time series data and the meteorological load peak time series data; generates the relative change of the cumulative effect value to the power load peak time series data based on the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data; generates the power load prediction result based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement result and the random variable, the meteorological load peak initial measurement result is calculated based on the pre-constructed meteorological load peak initial measurement model, introduces the cumulative effect of the temperature and humidity index on the basis of conventional meteorological elements, and calculates the influence of the unit change of the cumulative effect of the temperature and humidity index on the meteorological load peak, so as to improve the accuracy of the power load peak prediction result, thereby providing a scientific and effective basis for the summer power load prediction, especially the reasonable scheduling of the power load under continuous high temperature and high humidity meteorological conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0055] Figure 1 A flow chart of a method for predicting power load based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention;
[0056] Figure 2 A flow chart of another method for predicting power load based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention;
[0057] Figure 3 A meteorological load peak time series data distribution diagram provided by an embodiment of the present invention;
[0058] Figure 4 A comparison curve diagram of a daily meteorological load peak value and an initial measurement result of the meteorological load peak value provided by an embodiment of the present invention;
[0059] Figure 5 A schematic diagram of a fitting curve between a temperature and humidity index and a meteorological load peak value provided by an embodiment of the present invention;
[0060] Figure 6 A comparison diagram of the actual and predicted results of the meteorological load peak before and after the introduction of the temperature and humidity cumulative effect provided by an embodiment of the present invention;
[0061] Figure 7 A schematic diagram of the structure of a power load prediction device based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention;
[0062] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0064] It should be noted that the method and device for predicting electricity load based on the cumulative effect of temperature and humidity index disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field outside the field of artificial intelligence technology. The application field of the method and device for predicting electricity load based on the cumulative effect of temperature and humidity index disclosed in the present application is not limited.
[0065] The following takes the power load prediction device based on the cumulative effect of the temperature and humidity index as an example of the execution subject to illustrate the implementation process of the power load prediction method based on the cumulative effect of the temperature and humidity index provided by the embodiment of the present invention. It can be understood that the execution subject of the power load prediction method based on the cumulative effect of the temperature and humidity index provided by the embodiment of the present invention includes but is not limited to the power load prediction device based on the cumulative effect of the temperature and humidity index.
[0066] Figure 1 A flow chart of a method for predicting power load based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:
[0067] Step 101: extract data based on the acquired historical power load peak time series data for a specified time period to generate basic power load time series data and meteorological load peak time series data.
[0068] Step 102: Generate a cumulative effect value of the temperature and humidity index based on the acquired historical meteorological observation time series data, basic power load time series data, and meteorological load peak time series data.
[0069] Step 103: Generate a relative change of the cumulative effect value to the power load peak time series data based on the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data.
[0070] Step 104, generate a power load forecast result based on the relative change of the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak preliminary measurement results and random variables of the cumulative effect value. The meteorological load peak preliminary measurement results are calculated based on a pre-constructed meteorological load peak preliminary measurement model.
[0071] In the technical solution provided by the embodiment of the present invention, data extraction is performed based on the historical power load peak time series data of the specified time period obtained to generate basic power load time series data and meteorological load peak time series data; the cumulative effect value of the temperature and humidity index is generated based on the historical meteorological observation time series data, the basic power load time series data and the meteorological load peak time series data obtained; the relative change of the cumulative effect value to the power load peak time series data is generated based on the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data; the power load prediction result is generated based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement result and the random variable. The meteorological load peak initial measurement result is calculated based on the pre-constructed meteorological load peak initial measurement model. On the basis of conventional meteorological elements, the cumulative effect of the temperature and humidity index is introduced, and the influence of a unit change in the cumulative effect of the temperature and humidity index on the meteorological load peak is calculated, so as to improve the accuracy of the power load peak prediction result, thereby providing a scientific and effective basis for the summer power load prediction, especially the reasonable scheduling of the power load under continuous high temperature and high humidity meteorological conditions.
[0072] Figure 2 A flowchart of another method for predicting power load based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the method includes:
[0073] Step 201: Obtain historical power load peak time series data and historical meteorological observation time series data for a specified time period.
[0074] In the embodiment of the present invention, each step is performed by a power load prediction device based on the cumulative effect of temperature and humidity index.
[0075] In the embodiment of the present invention, the specified time period can be set according to actual needs, and the embodiment of the present invention does not limit this. As an optional solution, the specified time period is the summer (June-August) of the past three years.
[0076] In an embodiment of the present invention, the historical electricity load peak time series data is the daily electricity load peak value (i.e., daily peak electricity load) data of the measured area in summer (June-August) for at least three years, continuous, and quality controlled, obtained from the power department; the historical meteorological observation time series data is the meteorological observation data of the measured area in summer (June-August) for at least three years, continuous, and quality controlled, obtained from the meteorological department, and the meteorological observation data includes but is not limited to the daily maximum temperature, daily minimum temperature, daily average temperature, daily maximum relative humidity, daily minimum relative humidity, daily average relative humidity, daily maximum wind speed, daily minimum wind speed, daily average wind speed and daily precipitation.
[0077] For example: obtain the local daily historical power load peak time series data for the five years from June 1 to August 31, 2018 to 2022 from the local power department, and obtain the historical meteorological observation time series data for the current corresponding period from the meteorological department.
[0078] Step 202: Generate a linear trend value based on historical power load peak time series data.
[0079] Specifically, the slope of the historical power load peak time series data is calculated to obtain a linear tendency value.
[0080] Step 203: Generate basic power load time series data according to the linear tendency value, the preset basic constant term and the time series.
[0081] Specifically, through E0=a+b×t, the linear tendency value, the preset basic constant term and the time series are calculated to generate the basic power load time series data. Among them, E0 is the basic power load time series data, a is the basic constant term, b is the linear tendency value, and t is the time series.
[0082] For example: the annual basic electricity load of a certain place from 2018 to 2022 are 6097MW, 6221MW, 6300MW, 6412MW and 6457MW respectively.
[0083] Step 204: Subtract the historical power load peak time series data from the basic power load time series data to generate meteorological load peak time series data.
[0084] Specifically, through E w =E-E0, subtract the historical power load peak time series data from the basic power load time series data to generate the meteorological load peak time series data. w is the meteorological load peak time series data, E is the historical power load peak time series data, and E0 is the basic power load time series data.
[0085] Figure 3 A distribution diagram of meteorological load peak time series data provided by an embodiment of the present invention, such as Figure 3 As shown, taking the period from June 1 to August 31, 2018 to 2022 as an example, the horizontal axis is time and the vertical axis is the meteorological load peak (MW). The blue curve represents the distribution of the peak time series data of the power load in 2018, the red curve represents the distribution of the peak time series data of the power load in 2019, the green curve represents the distribution of the peak time series data of the power load in 2020, the purple curve represents the distribution of the peak time series data of the power load in 2021, and the orange curve represents the distribution of the peak time series data of the power load in 2022.
[0086] Step 205: perform correlation calculation based on the historical meteorological observation time series data and the meteorological load peak time series data to screen out significant meteorological factors.
[0087] Specifically, through Based on the historical meteorological observation time series data and the meteorological load peak time series data, the Pearson correlation coefficient between the daily meteorological load peak and various meteorological factors of the previous day is calculated. Among them, r is the Pearson correlation coefficient, X i is the meteorological observation data of the ith meteorological factor on the t-1th day, is the average value of the historical meteorological observation time series data, Y i is the peak meteorological load on day t, is the average value of the meteorological load peak time series data, and n is the total number of time series data.
[0088] It is worth noting that meteorological factors include but are not limited to daily maximum temperature, daily minimum temperature, daily average temperature, daily maximum relative humidity, daily minimum relative humidity, daily average relative humidity, daily maximum wind speed, daily minimum wind speed, daily average wind speed and daily precipitation.
[0089] In the embodiment of the present invention, the significant meteorological factors that pass the preset significance level are screened out through the significance test. As an optional solution, the preset significance level is 0.01, that is, α=0.01.
[0090] Taking meteorological factors including daily maximum temperature, daily minimum temperature, daily average temperature, daily average relative humidity, daily average wind speed and daily precipitation as an example, the Pearson correlation coefficient table is shown in Table 1:
[0091] Table 1
[0092]
[0093] Among them, ** indicates passing the significance test of α=0.01, and * indicates passing the significance test of α=0.05.
[0094] Taking the preset significance level of 0.01, that is, α = 0.01, as an example, the factors that pass the significance test of α = 0.01 are selected as significant meteorological factors, that is, the significant meteorological factors are daily maximum temperature, daily minimum temperature, daily average temperature, daily average relative humidity and daily precipitation.
[0095] Step 206: Based on the multiple regression method, a preliminary meteorological load peak measurement model is generated according to significant meteorological factors and partial regression coefficients.
[0096] Specifically, the significant meteorological factors are used as independent variables, and the meteorological load peak initial measurement model is established based on the multiple regression method, namely: w0 =a+a1X1+a2X2+…+a n X n Among them, E w0 is the initial measurement result of meteorological load peak, a is a constant, a1, a2, ..., a n is the partial regression coefficient, X n is the meteorological observation data of the nth significant meteorological factor.
[0097] For example, as shown in Table 1, the significant meteorological factors are the daily maximum temperature, daily minimum temperature, daily average temperature, daily average relative humidity and daily precipitation. The initial meteorological load peak measurement model constructed is:
[0098] E w0 =-6980.11+45.97X1+14.29X2+168.75X3+18.62X4-1.13X5
[0099] Among them, X1-X5 represent the daily maximum temperature, daily minimum temperature, daily average temperature, daily average relative humidity and daily precipitation of the previous day respectively.
[0100] Figure 4 A comparison curve diagram of a daily meteorological load peak value and a preliminary measurement result of the meteorological load peak value provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown in the figure, taking the period from June 1 to August 31, 2018 to 2022 as an example, the horizontal axis is time and the vertical axis is the meteorological load peak. The blue curve represents the distribution of the daily meteorological load peak, and the red curve represents the distribution of the meteorological load peak initial measurement results. The meteorological load peak initial measurement results are calculated based on the meteorological load peak initial measurement model constructed by the multiple regression method.
[0101] Step 207: Generate a temperature and humidity index time series based on the average temperature and the average relative humidity.
[0102] Specifically, through The average temperature and average relative humidity are calculated to generate a temperature and humidity index time series, where I is the temperature and humidity index time series, T is the average temperature (°C), and R is the average relative humidity (%).
[0103] It is worth noting that if the temperature and humidity index time series is time series data in days, then T is the daily average temperature and R is the daily average relative humidity.
[0104] Step 208: Generate a cumulative effect value of the temperature and humidity index based on the temperature and humidity index time series, basic power load time series data, and meteorological load peak time series data.
[0105] In the embodiment of the present invention, step 208 specifically includes:
[0106] Step 2081: Generate the meteorological time series variation of the power load based on the basic power load time series data and the meteorological load peak time series data.
[0107] Specifically, through The basic power load time series data and meteorological load peak time series data are calculated to generate the meteorological time series variation of power load. Among them, ΔE is the meteorological time series variation of power load, E w It is the meteorological load peak time series data, and E0 is the basic power load time series data.
[0108] Step 2082: Based on the preset temperature and humidity index threshold, the meteorological time series variation of the power load is screened and the average value is calculated according to the temperature and humidity index time series to generate the meteorological average variation of the power load.
[0109] In the embodiment of the present invention, the temperature and humidity index threshold value can be set according to actual needs, and the embodiment of the present invention does not limit this. As an optional solution, the temperature and humidity index threshold value is 600.
[0110] Specifically, the temperature and humidity index data greater than or equal to the temperature and humidity index threshold are screened out from the temperature and humidity index time series; the screened temperature and humidity index data are segmented, and the average value of the meteorological time series change of the power load corresponding to each segment is calculated to obtain the average meteorological change M of the power load.
[0111] For example, during the period from June to August of each year, when the temperature and humidity index I ≥ 600, the meteorological average change of the daily peak power load corresponding to the segment (I increases by 100 segments) is calculated, as shown in Table 2:
[0112] Table 2
[0113] Temperature and humidity index I range The average meteorological change of power load M [600,700) 6.70% [700,800) 7.10% [800,900) 8.20% [900,1000) 10.90% [1000,1100) 15.20% [1100,1200) 19.80% [1200,1300) 21.60% [1300,∞) 46.80%
[0114] Step 2083: Determine the critical value of the temperature and humidity index based on the temperature and humidity index time series.
[0115] In an embodiment of the present invention, the differences between the average meteorological changes of the power load corresponding to the temperature and humidity index data of adjacent segments after segmentation are compared, and the temperature and humidity index data corresponding to the adjacent change difference greater than the preset difference threshold is determined as the temperature and humidity index influence critical value.
[0116] For example, as shown in Table 2, when I ≥ 1000, the average change in the power load meteorology M increases significantly. Therefore, I = 1000 is used as the critical value of the temperature and humidity index, that is, I c =1000.
[0117] Figure 5 A schematic diagram of a fitting curve of a temperature and humidity index and a meteorological load peak provided by an embodiment of the present invention, such as Figure 5 As shown, the horizontal axis is the temperature and humidity index (dimensionless), the vertical axis is the peak value of meteorological load, the blue curve is the 95% confidence interval, and the red curve is the fitting curve. Figure 5 It can be seen that when the temperature and humidity index exceeds 1000, the peak value of the meteorological load rises rapidly, so I = 1000 is taken as the critical value of the temperature and humidity index (I c =1000) is reasonable.
[0118] Step 2084: Based on the critical value of the temperature and humidity index, cumulative cycle statistics are performed based on the temperature and humidity index time series to generate a cumulative cycle value.
[0119] In the embodiment of the present invention, the temperature and humidity index time series is compared with the temperature and humidity index impact critical value, and the cumulative number of days exceeding the temperature and humidity index impact critical value is calculated based on the preset initial cumulative number of days; the cumulative number of days calculated is determined as the cumulative cycle value. Specifically, the initial cumulative number of days is 1, and the cumulative cycle value is obtained by adding 1 every day from the initial cumulative number of days starting from the day when the temperature and humidity index exceeds the temperature and humidity index impact critical value in the temperature and humidity index time series; if the temperature and humidity index does not exceed the temperature and humidity index impact critical value, the cumulative cycle value is determined to be 0.
[0120] Step 2085: Generate a cumulative effect value of the temperature and humidity index according to the accumulated cycle value, the temperature and humidity index impact critical value and the acquired current temperature and humidity index.
[0121] Specifically, by A=k(II c ), calculate the cumulative cycle value, the critical value of the temperature and humidity index and the current temperature and humidity index, and generate the cumulative effect value of the temperature and humidity index. Where A is the cumulative effect value of the temperature and humidity index, k is the cumulative cycle value, I c is the critical value of the temperature and humidity index, and I is the current temperature and humidity index obtained.
[0122] Step 209: Generate a relative risk of the cumulative effect value to the peak value of the power load according to the cumulative effect value of the temperature and humidity index.
[0123] In the embodiment of the present invention, step 209 specifically includes:
[0124] Step 2091: Perform logarithmic curve fitting according to the preset expected value of power load and the cumulative effect value of temperature and humidity index to generate a fitting coefficient.
[0125] In the embodiment of the present invention, the peak time series data of meteorological load is used as the dependent variable, and the cumulative effect value of the temperature and humidity index as of the previous day is used as the independent variable, and the logarithmic relationship between the two is fitted as follows:
[0126] In[E(Ew)]=βA+α
[0127] Among them, E(Ew) is the expected value of the maximum daily power load, E w is the peak time series data of meteorological load, A is the cumulative effect value of temperature and humidity index, α is the fitting intercept, and β is the fitting coefficient. For meteorological factors with response threshold, the response threshold is used as the dividing point, and the fitting intercept α and fitting coefficient β are calculated in sections.
[0128] Step 2092: Based on the Poisson distribution, according to the change in the cumulative effect value of the fitting coefficient and the temperature and humidity index, generate the relative risk of the cumulative effect value to the peak value of the power load.
[0129] Specifically, based on the Poisson distribution theory, the relative change in the peak value of meteorological load caused by a unit change in the cumulative effect of temperature and humidity is calculated, which is the relative risk RR of the peak value of daily electricity load. i :
[0130] RR i =EXP(β.ΔA i )
[0131] Among them, RR i is the relative risk of the cumulative effect value to the peak value of power load, β is the fitting coefficient, ΔA i is the change in the cumulative effect of temperature and humidity.
[0132] Step 210: Generate the relative change of the cumulative effect value to the peak value of the power load based on the relative risk and the meteorological load peak time series data.
[0133] In the embodiment of the present invention, step 210 specifically includes:
[0134] Step 2101: Generate the relative change rate of the cumulative effect value to the peak value of the power load according to the relative risk.
[0135] Specifically, calculate the change rate ΔRR of the peak value of the meteorological daily electricity load caused by a unit change in the cumulative effect of temperature and humidity i :
[0136] ΔRR i =(RR i -1)×100%
[0137] Where ΔRR i is the relative change rate of the cumulative effect value to the peak value of power load, RR i It is the relative risk of the cumulative effect value to the peak value of power load.
[0138] For example, taking the above data as an example, when the temperature and humidity index exceeds 1000, the relative risk to the peak of meteorological load is 11.3% for every increase of 100.
[0139] Step 2102: multiply the relative change rate of the cumulative effect value to the peak value of the power load by the meteorological load peak time series data to generate the relative change of the cumulative effect value to the peak value of the power load.
[0140] Specifically, by ΔEw=ΔRR i ×Ew, multiply the relative change rate of the cumulative effect value to the peak power load by the meteorological load peak time series data to generate the relative change of the cumulative effect value to the peak power load, that is, the change of the daily peak power load caused by each unit change of the temperature and humidity index. Among them, ΔEw is the relative change of the cumulative effect value to the peak power load, ΔRR i is the relative change rate of the cumulative effect value to the peak value of power load, E w It is the time series data of meteorological load peak.
[0141] Step 211, generating a power load forecast result according to the relative change of the power load peak time series data, the basic power load time series data, the meteorological load peak initial measurement results and the random variable of the cumulative effect value.
[0142] In the embodiment of the present invention, the meteorological load peak initial measurement result is calculated based on a pre-built meteorological load peak initial measurement model. Specifically, the meteorological observation data of the current significant meteorological factors is obtained; the current meteorological observation data is input into the meteorological load peak initial measurement model E w0 =a+a1X1+a2X2+…+a n X n Calculate and generate the initial measurement results of the meteorological load peak. w0 is the initial measurement result of meteorological load peak, a is a constant, a1, a2, ..., a n is the partial regression coefficient, X n is the meteorological observation data of the nth significant meteorological factor.
[0143] Specifically, by E=E0+E w0+ΔEw+ε, the relative change of the cumulative effect value on the peak time series data of power load, the basic power load time series data, the initial measurement results of the meteorological load peak and the random variable are added to generate the power load forecast result. Among them, E is the power load forecast result; E w0 is the initial measurement result of the meteorological load peak; ΔEw is the relative change of the cumulative effect value to the peak power load; ε is a random variable.
[0144] It is worth noting that the influence of the random variable ε is very small and can be ignored in the embodiment of the present invention.
[0145] Figure 6 A comparison diagram of the actual and predicted results of the meteorological load peak before and after the introduction of the temperature and humidity cumulative effect is provided in an embodiment of the present invention, such as Figure 6 As shown, the horizontal axis is time, the vertical axis is the meteorological load peak, the blue curve is the actual curve, the red curve is the curve of the initial measurement result of the meteorological load peak, and the green curve is the curve of the power load forecast result after the temperature and humidity cumulative effect is introduced in this application. The high temperature and high humidity weather from July 29 to August 21, 2023 was tested. After the introduction of the cumulative effect of the temperature and humidity index, the forecast result has a smaller error with the actual meteorological load peak than when the cumulative effect is not considered, and the two values are closer, with an accuracy increase of 1.6 percentage points.
[0146] The present invention introduces the cumulative effect of temperature and humidity index on the basis of predicting the daily peak power load based on conventional meteorological elements, and calculates the impact of its unit change on the meteorological load peak, and then corrects the prediction result of the daily peak power load. It provides a scientific and effective basis for the prediction of summer power load, especially the reasonable scheduling of power load under continuous high temperature and high humidity meteorological conditions.
[0147] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.
[0148] It is worth noting that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0149] It is worth noting that the technical solution provided in this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.
[0150] In the technical solution of the power load prediction method based on the cumulative effect of the temperature and humidity index provided by the embodiment of the present invention, data extraction is performed according to the historical power load peak time series data of the specified time period obtained, and basic power load time series data and meteorological load peak time series data are generated; the cumulative effect value of the temperature and humidity index is generated according to the acquired historical meteorological observation time series data, the basic power load time series data and the meteorological load peak time series data; the relative change of the cumulative effect value to the power load peak time series data is generated according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data; the power load prediction result is generated according to the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement result and the random variable. The meteorological load peak initial measurement result is calculated according to the pre-constructed meteorological load peak initial measurement model. On the basis of conventional meteorological elements, the cumulative effect of the temperature and humidity index is introduced, and the influence of a unit change in the cumulative effect of the temperature and humidity index on the meteorological load peak is calculated, so as to improve the accuracy of the power load peak prediction result, thereby providing a scientific and effective basis for the summer power load prediction, especially the reasonable scheduling of the power load under continuous high temperature and high humidity meteorological conditions.
[0151] Figure 7 A schematic diagram of the structure of a power load prediction device based on the cumulative effect of temperature and humidity index provided by an embodiment of the present invention, the device is used to execute the power load prediction method based on the cumulative effect of temperature and humidity index, such as Figure 7 As shown, the device includes: a data extraction unit 11, a cumulative effect generation unit 12, a relative change amount generation unit 13 and a load prediction unit 14.
[0152] The data extraction unit 11 is used to extract data based on the acquired historical power load peak time series data of the specified time period, and generate basic power load time series data and meteorological load peak time series data.
[0153] The cumulative effect generating unit 12 is used to generate a cumulative effect value of the temperature and humidity index according to the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data.
[0154] The relative change amount generating unit 13 is used to generate the relative change amount of the cumulative effect value to the power load peak time series data according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data.
[0155] The load prediction unit 14 is used to generate a power load prediction result based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak preliminary measurement results and random variables. The meteorological load peak preliminary measurement results are calculated based on a pre-constructed meteorological load peak preliminary measurement model.
[0156] In an embodiment of the present invention, the data extraction unit 11 is specifically used to generate a linear tendency value based on historical power load peak time series data; generate basic power load time series data based on the linear tendency value, a preset basic constant term and a time series; and subtract the historical power load peak time series data from the basic power load time series data to generate meteorological load peak time series data.
[0157] In an embodiment of the present invention, the historical meteorological observation time series data includes the average temperature and the average relative humidity; the cumulative effect generation unit 12 is specifically used to generate a temperature and humidity index time series based on the average temperature and the average relative humidity; and to generate a cumulative effect value of the temperature and humidity index based on the temperature and humidity index time series, the basic power load time series data and the meteorological load peak time series data.
[0158] In an embodiment of the present invention, the cumulative effect generation unit 12 is specifically used to generate a meteorological time series variation of the power load based on the basic power load time series data and the meteorological load peak time series data; based on a preset temperature and humidity index threshold, the meteorological time series variation of the power load is screened and the average value is calculated according to the temperature and humidity index time series to generate an average meteorological variation of the power load; according to the temperature and humidity index time series, the critical value of the temperature and humidity index influence is determined; according to the temperature and humidity index time series, the cumulative cycle statistics are performed according to the temperature and humidity index time series to generate a cumulative cycle value; according to the cumulative cycle value, the critical value of the temperature and humidity index influence and the current temperature and humidity index obtained, the cumulative effect value of the temperature and humidity index is generated.
[0159] In an embodiment of the present invention, the relative change generation unit 13 is specifically used to generate a relative risk of the cumulative effect value to the peak power load based on the cumulative effect value of the temperature and humidity index; and to generate a relative change of the cumulative effect value to the peak power load based on the relative risk and the meteorological load peak time series data.
[0160] In an embodiment of the present invention, the relative change generation unit 13 is specifically used to perform logarithmic curve fitting according to a preset power load expected value and a cumulative effect value of the temperature and humidity index to generate a fitting coefficient; based on the Poisson distribution, the relative risk of the cumulative effect value to the power load peak is generated according to the fitting coefficient and the change in the cumulative effect value of the temperature and humidity index.
[0161] In an embodiment of the present invention, the relative change generation unit 13 is specifically used to generate a relative change rate of the cumulative effect value to the peak value of the power load according to the relative risk level; the relative change rate of the cumulative effect value to the peak value of the power load is multiplied by the meteorological load peak time series data to generate a relative change of the cumulative effect value to the peak value of the power load.
[0162] In the embodiment of the present invention, the device further includes: a correlation calculation unit 15 and a modeling unit 16 .
[0163] The correlation calculation unit 15 is used to perform correlation calculation based on the historical meteorological observation time series data and the meteorological load peak time series data to screen out significant meteorological factors.
[0164] The modeling unit 16 is used to generate a preliminary meteorological load peak measurement model based on a multiple regression method according to significant meteorological factors and partial regression coefficients.
[0165] In the scheme of the embodiment of the present invention, data extraction is performed based on the historical power load peak time series data of the specified time period obtained to generate basic power load time series data and meteorological load peak time series data; the cumulative effect value of the temperature and humidity index is generated based on the historical meteorological observation time series data, the basic power load time series data and the meteorological load peak time series data obtained; the relative change of the cumulative effect value to the power load peak time series data is generated based on the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data; the power load prediction result is generated based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement result and the random variable. The meteorological load peak initial measurement result is calculated based on the pre-constructed meteorological load peak initial measurement model. On the basis of conventional meteorological elements, the cumulative effect of the temperature and humidity index is introduced, and the influence of a unit change in the cumulative effect of the temperature and humidity index on the meteorological load peak is calculated, so as to improve the accuracy of the power load peak prediction result, thereby providing a scientific and effective basis for the summer power load prediction, especially the reasonable scheduling of the power load under continuous high temperature and high humidity meteorological conditions.
[0166] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0167] An embodiment of the present invention provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned method for predicting power load based on the cumulative effect of temperature and humidity index are implemented. For a specific description, please refer to the embodiment of the above-mentioned method for predicting power load based on the cumulative effect of temperature and humidity index.
[0168] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.
[0169] like Figure 8 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0170] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.
[0171] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611.
[0172] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0173] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0174] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0177] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0178] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0179] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.
[0180] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0181] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0182] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0183] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for predicting power load based on the cumulative effect of temperature and humidity index, It is characterized in that The method comprises: Data is extracted based on the acquired historical power load peak time series data for a specified time period to generate basic power load time series data and meteorological load peak time series data; Generate the cumulative effect value of the temperature and humidity index based on the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data; According to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data, generating a relative change amount of the cumulative effect value to the power load peak time series data; The power load forecast result is generated based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak preliminary measurement results and random variables. The meteorological load peak preliminary measurement results are calculated based on a pre-constructed meteorological load peak preliminary measurement model.
2. The power load prediction method based on the cumulative effect of temperature and humidity index according to claim 1, It is characterized in that The data extraction is performed based on the acquired historical power load peak time series data of the specified time period to generate basic power load time series data and meteorological load peak time series data, including: Generate a linear trend value according to the historical power load peak time series data; Generate the basic power load time series data according to the linear tendency value, the preset basic constant term and the time series; The historical power load peak time series data is subtracted from the basic power load time series data to generate the meteorological load peak time series data.
3. The power load prediction method based on the cumulative effect of temperature and humidity index according to claim 1, It is characterized in that The historical meteorological observation time series data include average temperature and average relative humidity; The method of generating a cumulative effect value of the temperature and humidity index based on the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data includes: Generate a temperature and humidity index time series according to the average temperature and average relative humidity; The cumulative effect value of the temperature and humidity index is generated according to the temperature and humidity index time series, the basic power load time series data and the meteorological load peak time series data.
4. The power load forecasting method based on the cumulative effect of temperature and humidity index according to claim 3, It is characterized in that The step of generating a cumulative effect value of the temperature and humidity index according to the temperature and humidity index time series, the basic power load time series data and the meteorological load peak time series data includes: Generate a meteorological time series variation of the power load according to the basic power load time series data and the meteorological load peak time series data; Based on the preset temperature and humidity index threshold, the power load meteorological time series variation is screened and the average value is calculated according to the temperature and humidity index time series to generate the power load meteorological average variation; Determining a critical value of the temperature and humidity index impact according to the temperature and humidity index time series; According to the critical value of the temperature and humidity index, cumulative cycle statistics are performed according to the time series of the temperature and humidity index to generate a cumulative cycle value; The cumulative effect value of the temperature and humidity index is generated according to the accumulated period value, the temperature and humidity index impact critical value and the acquired current temperature and humidity index.
5. The power load prediction method based on the cumulative effect of temperature and humidity index according to claim 1, It is characterized in that The step of generating a relative change amount of the cumulative effect value to the peak time series data of the power load according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data comprises: According to the cumulative effect value of the temperature and humidity index, generating a relative risk degree of the cumulative effect value to a peak value of power load; The relative change of the cumulative effect value to the peak power load is generated according to the relative risk and the meteorological load peak time series data.
6. The power load prediction method based on the cumulative effect of temperature and humidity index according to claim 5, It is characterized in that The step of generating a relative risk degree of the cumulative effect value to a peak value of power load according to the cumulative effect value of the temperature and humidity index comprises: Perform logarithmic curve fitting according to the preset expected value of power load and the cumulative effect value of temperature and humidity index to generate fitting coefficient; Based on the Poisson distribution, the relative risk of the cumulative effect value to the peak value of the power load is generated according to the change in the fitting coefficient and the cumulative effect value of the temperature and humidity index.
7. The power load prediction method based on the cumulative effect of temperature and humidity index according to claim 5, It is characterized in that The step of generating the relative change of the cumulative effect value to the peak value of the power load according to the relative risk degree and the meteorological load peak time series data comprises: Generating a relative change rate of the cumulative effect value to a peak value of power load according to the relative risk; The relative change rate of the cumulative effect value to the peak power load is multiplied by the meteorological load peak time series data to generate the relative change amount of the cumulative effect value to the peak power load.
8. The method for predicting power load based on the cumulative effect of temperature and humidity index according to claim 1, It is characterized in that Before generating the power load forecast result according to the relative change amount of the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement results and the random variables by the cumulative effect value, the method further includes: Perform correlation calculation based on the historical meteorological observation time series data and the meteorological load peak time series data to screen out significant meteorological factors; Based on the multiple regression method, a preliminary measurement model of the meteorological load peak is generated according to the significant meteorological factors and partial regression coefficients.
9. A power load prediction device based on the cumulative effect of temperature and humidity index, It is characterized in that The device comprises: A data extraction unit, used to extract data based on the acquired historical power load peak time series data of a specified time period, and generate basic power load time series data and meteorological load peak time series data; A cumulative effect generating unit, used to generate a cumulative effect value of a temperature and humidity index according to the acquired historical meteorological observation time series data, basic power load time series data and meteorological load peak time series data; A relative change amount generating unit, used for generating a relative change amount of the cumulative effect value to the power load peak time series data according to the cumulative effect value of the temperature and humidity index and the meteorological load peak time series data; The load forecasting unit is used to generate a power load forecasting result based on the relative change of the cumulative effect value to the power load peak time series data, the basic power load time series data, the pre-generated meteorological load peak initial measurement result and the random variable. The meteorological load peak initial measurement result is calculated based on a pre-constructed meteorological load peak initial measurement model.
10. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 9, It is characterized in that The data extraction unit is specifically used to generate a linear tendency value according to the historical power load peak time series data; Generate the basic power load time series data according to the linear tendency value, the preset basic constant term and the time series; The historical power load peak time series data is subtracted from the basic power load time series data to generate the meteorological load peak time series data.
11. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 9, It is characterized in that The historical meteorological observation time series data include average temperature and average relative humidity; The cumulative effect generating unit is specifically used to generate a temperature and humidity index time series according to the average temperature and average relative humidity; and to generate a cumulative effect value of the temperature and humidity index according to the temperature and humidity index time series, basic power load time series data and meteorological load peak time series data.
12. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 11, It is characterized in that The cumulative effect generating unit is specifically used to generate the meteorological time series variation of the power load according to the basic power load time series data and the meteorological load peak time series data; Based on the preset temperature and humidity index threshold, the power load meteorological time series variation is screened and the average value is calculated according to the temperature and humidity index time series to generate the power load meteorological average variation; Determining a critical value of the temperature and humidity index impact according to the temperature and humidity index time series; According to the critical value of the temperature and humidity index, cumulative cycle statistics are performed according to the time series of the temperature and humidity index to generate a cumulative cycle value; The cumulative effect value of the temperature and humidity index is generated according to the accumulated period value, the temperature and humidity index impact critical value and the acquired current temperature and humidity index.
13. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 9, It is characterized in that The relative change generation unit is specifically used to generate the relative risk of the cumulative effect value to the peak value of power load according to the cumulative effect value of the temperature and humidity index; and to generate the relative change of the cumulative effect value to the peak value of power load according to the relative risk and the time series data of the meteorological load peak.
14. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 13, It is characterized in that The relative change generation unit is specifically used to perform logarithmic curve fitting according to the preset expected value of power load and the cumulative effect value of the temperature and humidity index to generate a fitting coefficient; based on the Poisson distribution, according to the change of the fitting coefficient and the cumulative effect value of the temperature and humidity index, generate the relative risk of the cumulative effect value to the peak value of power load.
15. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 13, It is characterized in that The relative change generation unit is specifically used to generate the relative change rate of the cumulative effect value to the peak power load according to the relative risk; multiply the relative change rate of the cumulative effect value to the peak power load by the meteorological load peak time series data to generate the relative change of the cumulative effect value to the peak power load.
16. The power load prediction device based on the cumulative effect of temperature and humidity index according to claim 9, It is characterized in that The device also includes: A correlation calculation unit, used to perform correlation calculation based on the historical meteorological observation time series data and the meteorological load peak time series data, and screen out significant meteorological factors; The modeling unit is used to generate a preliminary measurement model of the meteorological load peak based on the multiple regression method according to the significant meteorological factors and partial regression coefficients.
17. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the power load prediction method based on the cumulative effect of the temperature and humidity index as described in any one of claims 1 to 8 is implemented.
18. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. It is characterized in that When the program instructions are loaded and executed by the processor, the power load prediction method based on the cumulative effect of the temperature and humidity index as described in any one of claims 1 to 8 is implemented.
19. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the method for predicting power load based on the cumulative effect of temperature and humidity index as described in any one of claims 1 to 8 is implemented.
