Electric power settlement method, system and equipment based on seasonal power utilization characteristics, and medium

Abstract

The invention discloses an electric power settlement method, system and device based on seasonal power consumption characteristics and a medium, and the method comprises the steps: carrying out the correlation analysis of predicted power consumption obtained through seasonal analysis of historical power consumption data through employing a gray correlation analysis method; and the electric power settlement information of the user in the corresponding season can be determined through the correlation analysis result, so that the problem of relatively large settlement error caused by the fact that the influence of the seasonal property on the electricity utilization characteristics of the user is not considered in the current electric power settlement is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity consumption feature analysis, and particularly to a power settlement method, system, device and medium based on seasonal electricity consumption features. Background Art

[0002] In the spot market environment, the settlement of the retail market needs to take into account the power and electricity balance characteristics of each region and the diversity of retail packages. First of all, the power and electricity balance has obvious seasonal characteristics. Especially in the wet season and the dry season, there are significant differences in the market-based power settlement. This seasonal fluctuation poses higher requirements for power companies. Power companies need to conduct targeted analysis based on seasonal electricity consumption characteristics to ensure stable power supply for users in different seasons.

[0003] In the prior art, there are many settlement methods for power trading. For example, a spot trading electricity bill settlement method based on user electricity consumption characteristics disclosed in Chinese Patent Application Publication No. CN116128645A takes into account the electricity consumption characteristics and electricity consumption distribution of different electricity consumption types of users at the peak-valley periods of the metering points, and realizes the guiding effect of the spot market price on user electricity consumption characteristics. This patent considers the electricity consumption characteristics at the peak-valley periods of the metering points, but does not consider the electricity consumption characteristics affected by seasonality.

[0004] Without considering the influence of seasonality on electricity consumption characteristics, it is impossible to conduct targeted power settlement for the wet season and the dry season, resulting in power settlement not conforming to seasonal characteristics, and thus power companies cannot ensure stable power supply for users in different seasons. Summary of the Invention

[0005] Based on the problems raised in the above background art, the purpose of the present invention is to provide a power settlement method, system, device and medium based on seasonal electricity consumption characteristics, which solves the problem that without considering the influence of seasonality on electricity consumption characteristics, it is impossible to conduct targeted power settlement for the wet season and the dry season, resulting in power settlement not conforming to seasonal characteristics, and thus power companies cannot ensure stable power supply for users in different seasons.

[0006] The present invention is achieved by the following technical solutions:

[0007] The first aspect of the present invention provides a power settlement method based on seasonal electricity consumption characteristics, including the following steps:

[0008] Obtain the historical electricity consumption data of the user within a preset time;

[0009] Calculate the historical electricity consumption data to obtain a periodic electricity consumption sequence and a non-periodic electricity consumption sequence that fluctuate with seasonality for the historical electricity consumption data;

[0010] Perform feature analysis on the periodic electricity consumption sequence and the aperiodic electricity consumption sequence to obtain periodic features and aperiodic features;

[0011] Construct a deviation probability model based on the periodic features and the aperiodic features, and perform electricity consumption prediction through the deviation probability model to obtain the predicted electricity consumption;

[0012] Use the grey relational analysis method to perform relational analysis on the predicted electricity consumption, and determine the electricity settlement plan according to the results of the relational analysis.

[0013] In the above technical solution, obtain the historical electricity consumption data of the user within a preset time, and fit the historical electricity consumption data within the preset time with the meteorological data according to the physical relationship between the electricity consumption data and the meteorological factors to generate a periodic electricity consumption sequence and an aperiodic electricity consumption sequence that fluctuate seasonally.

[0014] Among them, the periodic electricity consumption sequence and the aperiodic electricity consumption sequence reflect the seasonal electricity consumption characteristics of the user. Feature analysis is performed using the electricity consumption characteristics including the user's seasonality, and different characteristics of the user's electricity consumption with the change of seasonal meteorology are obtained. Among them, due to the periodicity and aperiodicity of seasonality, in this method, it is divided into periodic features and aperiodic features to adapt to the meteorological characteristics of different seasons.

[0015] Construct a deviation probability model according to the aforementioned periodic features and aperiodic features. The deviation probability model refers to the electricity consumption deviation value under the periodic seasonal features and aperiodic seasonal features. Using this deviation probability model, the predicted electricity consumption of the user under specific seasonal conditions can be predicted.

[0016] Finally, use the grey relational analysis method to perform relational analysis on the above predicted electricity consumption. Through the results of the relational analysis, the electricity settlement information of the user under the corresponding season can be determined, thereby overcoming the problem of large settlement errors caused by the current electricity settlement not considering the influence of seasonality on the user's electricity consumption characteristics.

[0017] In an alternative embodiment, calculate the historical electricity consumption data to obtain a periodic electricity consumption sequence and an aperiodic electricity consumption sequence that fluctuate seasonally for the historical electricity consumption data, including the following steps:

[0018] Obtain meteorological data, and use the curve fitting method to fit the historical electricity consumption data with the meteorological data to obtain the relationship between electricity consumption and meteorological changes;

[0019] Perform periodic identification on the meteorological data to obtain the periodicity of the meteorological data;

[0020] Screen out the periodic electricity consumption sequence and the aperiodic electricity consumption sequence from the historical electricity consumption data according to the described electrical meteorological change relationship and the periodicity of the meteorological data.

[0021] In an alternative embodiment, perform feature analysis on the periodic electricity consumption sequence to obtain periodic features, including the following steps:

[0022] Calculate the average value of the periodic electricity consumption sequence, and the average value is used to reflect the electricity consumption level of the season;

[0023] Calculate the standard deviation of the periodic electricity consumption sequence based on the average value, and the standard deviation is used to measure the degree of dispersion of the electricity consumption data within the season;

[0024] Calculate the coefficient of variation of the periodic electricity consumption sequence according to the average value and the standard deviation, and the coefficient of variation is used to compare the relative magnitudes of the electricity consumption fluctuations between different seasons;

[0025] Determine the periodic features of the periodic electricity consumption sequence according to the average value, the standard deviation, and the coefficient of variation.

[0026] In an alternative embodiment, perform feature analysis on the aperiodic electricity consumption sequence to obtain aperiodic features, including the following steps:

[0027] Sort the aperiodic electricity consumption sequence according to the numerical magnitude to obtain a sorted aperiodic electricity consumption sequence;

[0028] Obtain the maximum value and the minimum value of the sorted aperiodic electricity consumption sequence, and calculate the range of the aperiodic electricity consumption sequence by using the maximum value and the minimum value;

[0029] Perform quartile division on the sorted aperiodic electricity consumption sequence to obtain the first quartile, the second quartile, and the third quartile;

[0030] Calculate the interquartile range of the aperiodic electricity consumption sequence by using the first quartile and the third quartile;

[0031] Determine the aperiodic features of the aperiodic electricity consumption sequence according to the range and the interquartile range.

[0032] In an alternative embodiment, construct a deviation probability model according to the periodic features, including the following steps:

[0033] Determine the statistical features of the periodic features in the periodic fluctuation;

[0034] Construct a periodic electricity consumption prediction model according to the statistical features; wherein, the periodic electricity consumption prediction model includes a non-trend prediction model and a trend prediction model;

[0035] Construct an aperiodic deviation probability model and a trend deviation probability model based on the statistical features in combination with the detrended prediction model and the trend prediction model.

[0036] In an alternative embodiment, constructing a deviation probability model based on the aperiodic features includes the following steps:

[0037] Establish an event probability model using the aperiodic features;

[0038] Construct an electricity consumption prediction model according to the event probability model;

[0039] Construct an electricity consumption prediction deviation probability model based on the event probability features in combination with the electricity consumption prediction model.

[0040] In an alternative embodiment, constructing an electricity consumption prediction deviation probability model based on the event probability features in combination with the electricity consumption prediction model includes the following steps:

[0041] Randomly generate event samples using the event probability model;

[0042] If the event sample is an occurrence sample, randomly draw an electricity consumption sample from the additional electricity consumption distribution corresponding to the event sample;

[0043] Perform electricity consumption prediction using the electricity consumption prediction model to obtain a periodic electricity consumption prediction value;

[0044] Superimpose the electricity consumption sample on the periodic electricity consumption prediction value to obtain a total electricity consumption simulation sample;

[0045] Calculate the prediction deviation between the total electricity consumption simulation sample and the total electricity consumption prediction value;

[0046] Repeat the calculation process of the prediction deviation N times to obtain a statistical prediction deviation, and use the statistical prediction deviation as the probability estimate of the electricity consumption prediction deviation probability model.

[0047] The second aspect of the present invention provides a power settlement system based on seasonal electricity consumption characteristics, including:

[0048] A data acquisition module for acquiring historical electricity consumption data of a user within a preset time;

[0049] An electricity consumption sequence calculation module for calculating the historical electricity consumption data to obtain a periodic electricity consumption sequence and an aperiodic electricity consumption sequence of the historical electricity consumption data fluctuating with seasons;

[0050] A feature analysis module for performing feature analysis on the periodic electricity consumption sequence and the aperiodic electricity consumption sequence to obtain periodic features and aperiodic features;

[0051] The power consumption prediction module is used to construct a deviation probability model based on the periodic characteristics and the aperiodic characteristics, and perform power consumption prediction through the deviation probability model to obtain the predicted power consumption.

[0052] The settlement correlation analysis module is used to perform correlation analysis on the predicted power consumption by using the grey correlation analysis method, and determine the power settlement plan according to the correlation analysis result.

[0053] The third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, a power settlement method based on seasonal power consumption characteristics is implemented.

[0054] The fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a power settlement method based on seasonal power consumption characteristics is implemented.

[0055] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0056] The present invention performs correlation analysis on the predicted power consumption obtained by seasonal analysis of historical power consumption data by using the grey correlation analysis method. Through the correlation analysis result, the power settlement information of the user in the corresponding season can be determined, thereby overcoming the problem of large settlement errors caused by the current power settlement not considering the influence of seasonality on the user's power consumption characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0058] Figure 1 It is a schematic flow chart of the power settlement method based on seasonal power consumption characteristics provided by Embodiment 1 of the present invention;

[0059] Figure 2 It is a schematic structural diagram of the power settlement system based on seasonal power consumption characteristics provided by Embodiment 2 of the present invention;

[0060] Figure 3 It is a schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] To make the objectives, technical solutions, and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with embodiments and the accompanying drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and do not limit the present invention.

[0062] Embodiment 1

[0063] Figure 1 As shown in the flowchart of the power settlement method based on seasonal electricity consumption characteristics provided by Embodiment 1 of the present invention, Figure 1 as shown, the power settlement method based on seasonal electricity consumption characteristics includes the following steps:

[0064] Obtain the historical electricity consumption data of the user within a preset time;

[0065] Calculate the historical electricity consumption data to obtain the periodic electricity consumption sequence and the non-periodic electricity consumption sequence that fluctuate with seasons for the historical electricity consumption data;

[0066] Conduct feature analysis on the periodic electricity consumption sequence and the non-periodic electricity consumption sequence to obtain periodic features and non-periodic features;

[0067] Construct a deviation probability model based on the periodic features and the non-periodic features, and conduct electricity consumption prediction through the deviation probability model to obtain the predicted electricity consumption;

[0068] Use the grey relational analysis method to conduct relational analysis on the predicted electricity consumption, and determine the power settlement plan according to the results of the relational analysis.

[0069] It should be noted that in the case of not considering the influence of seasons on electricity consumption characteristics, it is impossible to conduct targeted power settlement for the wet season and the dry season, resulting in the power settlement not conforming to seasonal characteristics, thus causing the power company to be unable to ensure stable power supply for users in different seasons. The present invention proposes a power settlement method based on seasonal electricity consumption characteristics. First, obtain the historical electricity consumption data of the user within a preset time, and fit the historical electricity consumption data within the preset time with meteorological data according to the physical relationship existing between the electricity consumption data and meteorological factors to generate a periodic electricity consumption sequence and a non-periodic electricity consumption sequence that fluctuate with seasons.

[0070] Among them, the periodic electricity consumption sequence and the non-periodic electricity consumption sequence reflect the seasonal electricity consumption characteristics of the user. Feature analysis is carried out using the electricity consumption characteristics including the user's seasonality to obtain different characteristics of the user's electricity consumption with the change of seasonal meteorology. Among them, due to the periodicity and non-periodicity of seasons, in this method, they are divided into periodic features and non-periodic features to adapt to the meteorological characteristics of different seasons.

[0071] Construct a deviation probability model based on the aforementioned periodic and aperiodic characteristics. This deviation probability model refers to the electricity consumption deviation values under periodic seasonal characteristics and aperiodic seasonal characteristics. Using this deviation probability model, the predicted electricity consumption of users under specific seasonal conditions can be predicted.

[0072] Finally, use the grey relational analysis method to conduct a relational analysis on the above predicted electricity consumption. Through the results of the relational analysis, the electricity settlement information of users under the corresponding season can be determined, thereby overcoming the problem of large settlement errors caused by the current electricity settlement not considering the impact of seasonality on user electricity consumption characteristics.

[0073] In an optional embodiment, calculate the historical electricity consumption data to obtain the periodic electricity consumption sequence and aperiodic electricity consumption sequence that fluctuate with seasonality of the historical electricity consumption data, including the following steps:

[0074] Obtain meteorological data, and use the curve fitting method to fit the historical electricity consumption data with the meteorological data to obtain the relationship between electricity consumption and meteorological changes;

[0075] Conduct periodic identification on the meteorological data to obtain the periodicity of the meteorological data;

[0076] Screen out the periodic electricity consumption sequence and aperiodic electricity consumption sequence from the historical electricity consumption data according to the relationship between electricity consumption and meteorological changes and the periodicity of the meteorological data.

[0077] In this embodiment, the historical electricity consumption data includes the electricity consumption of users and the corresponding electricity settlement data.

[0078] To study the seasonal electricity consumption characteristics caused by the influence of user electricity consumption data and meteorological data, in this embodiment, the curve fitting method is used to fit the historical electricity consumption data and meteorological data to obtain the relationship between electricity consumption data and meteorological changes.

[0079] In this embodiment, according to the physical relationship between electricity consumption data and meteorological factors, the least squares method is used for fitting. Specifically, assume there are n groups of electricity consumption data y i and the corresponding meteorological data x i (i = 1, 2,..., n). For the linear fitting function y = a + bx, the goal of the least squares method is to minimize the sum of squared errors Find the partial derivatives of S with respect to a and b respectively.

[0080] Let the sum of squared errors be minimized to 0, and the equations for solving a and b can be obtained:

[0081]

[0082] By solving the above equations, the values of the fitting parameters a and b can be obtained. Substituting the fitting parameters a and b into the linear fitting function completes the fitting of historical electricity consumption data and meteorological data.

[0083] Further, use the correlation coefficient R 2 to evaluate the fitting effect. Among them is the value predicted by the fitting function, is the average value of y i . The value of R 2 ranges between 0 and 1. The closer it is to 1, the better the fitting effect.

[0084] For meteorological data, it has certain periodicity. For example, the daily cycle of temperature (high during the day and low at night), annual cycle, and seasonal temperature changes. Taking the annual cycle as an example, by analyzing meteorological data over the years, the typical meteorological feature range of each season can be determined, such as the average temperature range in spring, the highest temperature range in summer, etc.

[0085] At the same time, there is also a certain non - periodicity in meteorological data. For example, sudden extreme weather events, such as heavy rain, heavy snow, or cold snaps.

[0086] According to the fitting relationship between electricity consumption data and meteorological data and the periodicity of meteorological factors, periodic electricity consumption sequences are screened out. For example, if there is an annual cycle relationship between electricity consumption and temperature next year, and the changes in temperature and electricity consumption are relatively stable within each season, then the part of the electricity consumption data that conforms to this seasonal cycle law is extracted as the periodic electricity consumption sequence.

[0087] In this embodiment, meteorological data is divided according to seasons, and for each season, the corresponding electricity consumption data points are found, and these electricity consumption data points form a periodic electricity consumption sequence. For example, for the periodic electricity consumption sequence in summer, the electricity consumption data corresponding to the temperature within the typical range in summer, such as 25 - 35 degrees Celsius, can be selected.

[0088] The non - periodic electricity consumption sequence is obtained by excluding the periodic electricity consumption sequence. In this embodiment, key attention is paid to those electricity consumption data points related to non - periodic meteorological events. For example, during extreme heavy rain weather, due to the possible need to use drainage equipment, lighting equipment for emergency repair, etc., the electricity consumption data will show abnormal peaks. These electricity consumption data points corresponding to non - periodic meteorological events and the electricity consumption data points that cannot be explained by meteorological cycle laws form the non - periodic electricity consumption sequence. By comparing the actual electricity consumption data with the electricity consumption data predicted according to the fitting relationship and meteorological cycle, non - periodic data points are identified, and the data points with large differences are classified as non - periodic electricity consumption sequences.

[0089] In an alternative embodiment, the periodic electricity consumption sequence is subjected to feature analysis to obtain periodic features, including the following steps:

[0090] Calculate the average value of the periodic power consumption sequence, and the average value is used to reflect the power consumption level of the season;

[0091] Calculate the standard deviation of the periodic power consumption sequence based on the average value, and the standard deviation is used to measure the degree of dispersion of the power consumption data within the season;

[0092] Calculate the coefficient of variation of the periodic power consumption sequence according to the average value and the standard deviation, and the coefficient of variation is used to compare the relative magnitudes of the power consumption fluctuations between different seasons;

[0093] Determine the periodic characteristics of the periodic power consumption sequence according to the average value, the standard deviation, and the coefficient of variation.

[0094] Among them, the average value is calculated as follows:

[0095]

[0096] In the above formula, is the average value, y pi is the data point in the periodic power consumption sequence, n p is the number of data points in the periodic power consumption sequence.

[0097] Among them, the standard deviation is calculated as follows:

[0098]

[0099] In the above formula, σ p is the standard deviation.

[0100] Among them, the coefficient of variation is calculated as follows:

[0101]

[0102] Among them, V p is the coefficient of variation.

[0103] By observing the periodic power consumption sequence, determine the time when the power consumption peaks and troughs occur in each season. For example, in summer, it may be found that the power consumption peak occurs between 2-6 pm and 7-10 pm, which is related to temperature changes and the patterns of residents' activities. At the same time, confirm the length of the seasonal cycle, generally in years, and the stability of the seasonal cycle can be verified by analyzing data over multiple years.

[0104] In an alternative embodiment, perform feature analysis on the non-periodic power consumption sequence to obtain non-periodic features, including the following steps:

[0105] Sort the non-periodic power consumption sequence according to the numerical size to obtain a sorted non-periodic power consumption sequence;

[0106] Obtain the maximum and minimum values of the sorted aperiodic power consumption sequence, and calculate the range of the aperiodic power consumption sequence by using the maximum value and the minimum value;

[0107] Perform quartile division on the sorted aperiodic power consumption sequence to obtain the first quartile, the second quartile, and the third quartile;

[0108] Calculate the interquartile range of the aperiodic power consumption sequence by using the first quartile and the third quartile;

[0109] Determine the aperiodic characteristics of the aperiodic power consumption sequence according to the range and the interquartile range.

[0110] Among them, the range is calculated as follows:

[0111] R = max(y np ) - min(y np );

[0112] In the above formula, R is the range, and y np is the data point in the aperiodic power consumption sequence.

[0113] Among them, the interquartile range is calculated as follows:

[0114] IQR = Q3 - Q1;

[0115] In the above formula, IQR is the interquartile range, Q3 is the third quartile, and Q1 is the first quartile.

[0116] It should be noted that the range can reflect the maximum amplitude of the aperiodic power consumption change. For example, if the range is very large, it indicates that the aperiodic event has a greater impact on the power consumption data. The interquartile range is an index in statistics to measure the degree of data dispersion, and it represents the degree of dispersion of the middle 50% of the data. The interquartile range is not affected by extreme values or outliers. Therefore, when there are outliers in the aperiodic power consumption sequence, it can more robustly describe the fluctuation of the aperiodic power consumption.

[0117] Associate the power consumption peak and fluctuation in the aperiodic power consumption sequence with specific aperiodic events, such as extreme weather, social activities, etc. The causal relationship between the event and the change in power consumption data can be determined by checking the event records. For example, when there is an aperiodic power consumption peak, check whether there is a corresponding record of heavy rain weather. If so, it may be due to power repair and other power consumption behaviors caused by heavy rain. At the same time, analyze the impact degree of different types of aperiodic events on the power consumption. For example, the increase amplitude of power consumption caused by large-scale social activities may be different from the increase amplitude of power consumption for emergency repair caused by natural disasters. Evaluate the impact degree by comparing the changes in power consumption data corresponding to these events.

[0118] In an alternative embodiment, constructing a deviation probability model according to the periodic characteristics includes the following steps:

[0119] Determine the statistical characteristics of the periodic characteristics in the periodic fluctuation;

[0120] Construct a periodic electricity consumption prediction model according to the statistical characteristics; wherein, the periodic electricity consumption prediction model includes a non-trend prediction model and a trend prediction model;

[0121] Construct a non-trend deviation probability model and a trend deviation probability model based on the statistical characteristics in combination with the non-trend prediction model and the trend prediction model.

[0122] In the previous step, the characteristics of the data points in the periodic electricity consumption sequence were calculated. In this step, the characteristics of the periodic electricity consumption sequence are calculated based on the periodic characteristics obtained in the previous step. In this embodiment, the characteristics are represented in the form of statistical characteristics.

[0123] Specifically, determining the statistical characteristics of the periodic characteristics in the periodic fluctuation includes:

[0124] Mean value :

[0125]

[0126] Standard deviation :

[0127]

[0128] In the above formula, s is the season type, s = 1, 2, 3, 4 represent the four seasons of spring, summer, autumn and winter, is the periodic electricity consumption sequence, p is the periodicity, n s is the number of periodic electricity consumption data points in season s, is the i-th periodic electricity consumption data point in season s.

[0129] Furthermore, even under the same seasonal meteorological conditions, the periodic electricity consumption may show the electricity consumption situation under a certain trend or may not show an electricity consumption trend. Therefore, in this embodiment, a fitting linear regression model is needed to describe the linear trend of the periodic electricity consumption over time, and then the periodic electricity consumption is predicted according to the linear trend.

[0130] Specifically, use a fitting linear regression model to describe the linear trend of the periodic electricity consumption over time:

[0131]

[0132] In the above formula, t is the time, αs is the intercept, β s is the slope, is the linear trend, ∈ s,t is the error term.

[0133] Under the condition of the above linear trend, a power consumption prediction model is constructed. Among them, the prediction model construction in the case of no trend is as follows:

[0134]

[0135] In the above formula, is the periodic prediction value of power consumption, predicts the central fluctuation of the periodic power consumption in season s, is the degree of fluctuation.

[0136] The prediction model considering the trend is constructed as follows:

[0137]

[0138] Among them, by calculating the regression coefficients α s and β s to evaluate the uncertainty of power consumption by the standard error.

[0139] Based on the power consumption prediction model, a deviation probability model is constructed. Among them, since the prediction model in the case of no trend follows a normal distribution then also follows a normal distribution, with its mean being and variance being

[0140] Calculate the probability that the power consumption prediction deviation exceeds a certain threshold k According to the properties of the normal distribution, where Ф(·) is the cumulative distribution function of the standard normal distribution

[0141] According to the above analysis, the no-trend deviation probability model in this embodiment is constructed as follows:

[0142]

[0143] In the above formula, is the periodic part of the actual power consumption, is the periodic prediction value of power consumption, is the deviation value under no trend.

[0144] Furthermore, due to the uncertainty of trend estimation, the distribution of will be more complex. Assume that the estimated standard errors of the regression coefficients and are SE αs and SE βs , estimated by simulation The probability that the distribution and prediction deviation exceed a certain threshold. The specific simulation process is as follows: According to the distribution of α s and β s Samples are randomly drawn, the prediction deviation is calculated, and after repeating multiple times, the probability that the deviation exceeds the threshold is statistically analyzed.

[0145] According to the above analysis, the trend deviation probability model is constructed as follows:

[0146]

[0147] In the above formula, is, α s and β s are the intercept and slope, t is time, is the deviation value under the trend.

[0148] In an optional embodiment, a deviation probability model is constructed according to the aperiodic characteristics, including the following steps:

[0149] An event probability model is established using the aperiodic characteristics;

[0150] An electricity consumption prediction model is constructed according to the event probability model;

[0151] Based on the event probability characteristics and combined with the electricity consumption prediction model, an electricity consumption prediction deviation probability model is constructed.

[0152] For establishing the event probability model, it is assumed that there are m different types of aperiodic events E j (j = 1, 2,..., m), such as natural disaster events, social activity events, etc. The probability P(E j ) of each event occurring is statistically analyzed through historical data. For example, in the past T years, the event E j occurred n j times, then When the event E j occurs, it is assumed that the additional electricity consumption ΔY j follows a normal distribution ΔY j ~N(μ j , σ j 2 ). μ j and σ j 2 are estimated by analyzing the electricity consumption data when the event occurs in historical data. For example, for a certain natural disaster event, the average value of the additional electricity consumption each time the event occurs is calculated as μ j , and its standard deviation is calculated as σ j .

[0153] In this embodiment, constructing an electricity consumption prediction model according to the event probability model includes: the total predicted electricity consumption Y consists of a periodic part Y p , with a predicted value of and an aperiodic part. The aperiodic part takes into account the occurrence of events, that is:

[0154]

[0155] where I j is an indicator variable. When the event E j occurs, I j = 1; otherwise, I j = 0.

[0156] In an alternative embodiment, based on the event probability characteristics and in combination with the electricity consumption prediction model, constructing an electricity consumption prediction deviation probability model includes the following steps:

[0157] Randomly generate event samples using the event probability model;

[0158] If the event sample is an occurrence sample, randomly draw an electricity consumption sample from the additional electricity consumption distribution corresponding to the event sample;

[0159] Use the electricity consumption prediction model to predict electricity consumption and obtain a periodic electricity consumption prediction value;

[0160] Superimpose the electricity consumption sample on the periodic electricity consumption prediction value to obtain a total electricity consumption simulation sample;

[0161] Calculate the prediction deviation between the total electricity consumption simulation sample and the total electricity consumption prediction value;

[0162] Repeat the calculation process of the prediction deviation N times to obtain a statistical prediction deviation, and use the statistical prediction deviation as the probability estimate of the electricity consumption prediction deviation probability model.

[0163] In this embodiment, define the prediction deviation where is the total electricity consumption prediction value. Due to the uncertainty of aperiodic events, the distribution of ΔY is relatively complex, and the deviation probability is estimated through Monte Carlo simulation. The specific steps are as follows:

[0164] Randomly generate samples of whether the event occurs according to the event occurrence probability P(E j ). For example, generate a random number between 0 and 1. If it is less than P(E j ), it is considered that the event occurs.

[0165] For the occurring event, from the corresponding additional electricity consumption distribution Randomly select a sample from it and superimpose these samples on the predicted value of periodic power consumption to obtain a simulated sample Y of total power consumption sin .

[0166] Calculate the prediction deviation of the simulated sample Repeat the above process N times and count the prediction deviation ΔY sin The proportion exceeding a certain threshold is used as the probability estimate that the power consumption prediction deviation exceeds this threshold

[0167] Furthermore, use the grey relational analysis method to conduct a relational analysis on the predicted power consumption, including

[0168] Take the predicted power consumption as the reference sequence and set several standardized power settlements as the comparison sequences. Specifically, set several standardized power settlements as x0(k), x1(k), … x i (k), where k is the test serial number

[0169] Conduct data dimensionless processing based on the reference sequence and the comparison sequences. Specifically, the data dimensionless processing process is as follows

[0170]

[0171]

[0172] After data dimensionless processing, calculate the grey correlation coefficient and grey relational degree respectively. Specifically, the grey correlation coefficient ξ i (k):

[0173]

[0174] The grey relational degree γ j :

[0175]

[0176] In the above formula, x ′ 0(k) is the predicted power consumption, x i ′ (k) is the i-th standardized power settlement, and ρ is the resolution coefficient

[0177] Analyze the correlation between the predicted power consumption and the standardized power settlements through grey relational analysis, and then screen multiple power settlement schemes that meet the conditions and their corresponding matching priorities according to the correlation

[0178] Further, for the matching priority, in this embodiment, a correlation threshold can be set by those skilled in the art for matching. The electricity settlement with a higher correlation is set within the threshold range, and conversely, the electricity settlement with a very low correlation is not within the threshold range. Through this setting, the electricity settlement plan matching the user's seasonal electricity consumption characteristics can be quickly found.

[0179] Embodiment 2

[0180] Figure 2 FIG. is a schematic structural diagram of a power settlement system based on seasonal electricity consumption characteristics provided in Embodiment 2 of the present invention. As Figure 2 shown, the power settlement system based on seasonal electricity consumption characteristics includes:

[0181] A data acquisition module for acquiring historical electricity consumption data of a user within a preset time;

[0182] An electricity consumption sequence calculation module for calculating the historical electricity consumption data to obtain a periodic electricity consumption sequence and an aperiodic electricity consumption sequence of the historical electricity consumption data fluctuating with seasons;

[0183] A feature analysis module for performing feature analysis on the periodic electricity consumption sequence and the aperiodic electricity consumption sequence to obtain periodic features and aperiodic features;

[0184] An electricity consumption prediction module for constructing a deviation probability model according to the periodic features and the aperiodic features, and performing electricity consumption prediction through the deviation probability model to obtain predicted electricity consumption;

[0185] A settlement correlation analysis module for performing correlation analysis on the predicted electricity consumption by using the grey correlation analysis method, and determining an electricity settlement plan according to the correlation analysis result.

[0186] Embodiment 3

[0187] Figure 3 FIG. is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention. As Figure 3 shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 3 Taking one processor 21 as an example; the processor 21, the memory 22, the input device 23, and the output device 24 in the electronic device can be connected through a bus or other means. Figure 3 Taking the connection through a bus as an example.

[0188] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules. By running the software programs, instructions, and modules stored in the memory 22, the processor 21 executes various functional applications and data processing of the electronic device, that is, implements the power settlement method based on seasonal electricity consumption characteristics in Embodiment 1.

[0189] The memory 22 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 22 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 22 may further include a memory remotely set relative to the processor 21, and these remote memories can be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The input device 23 can be used to receive user input such as an id and a password. The output device 24 is used to output a power distribution page.

[0191] Embodiment 4

[0192] Embodiment 4 of the present invention also provides a computer-readable storage medium, and the computer-executable instructions are used to implement the power settlement method based on seasonal electricity consumption characteristics provided in Embodiment 1 when executed by a computer processor.

[0193] A storage medium containing computer-executable instructions provided in the embodiments of the present invention, the computer-executable instructions are not limited to the method operations provided in Embodiment 1, and can also execute related operations in the power settlement method based on seasonal electricity consumption characteristics provided in any embodiment of the present invention.

[0194] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A power settlement method based on seasonal electricity consumption characteristics, characterized in that It includes the following steps: Obtain the historical electricity consumption data of the user within a preset time; Calculate the historical electricity consumption data to obtain a periodic electricity consumption sequence and an aperiodic electricity consumption sequence that fluctuate seasonally; Conduct feature analysis on the periodic electricity consumption sequence and the aperiodic electricity consumption sequence to obtain periodic features and aperiodic features; Construct a deviation probability model based on the periodic features and the aperiodic features, and perform electricity consumption prediction through the deviation probability model to obtain the predicted electricity consumption; Use the grey relational analysis method to conduct relational analysis on the predicted electricity consumption, and determine the electricity settlement plan according to the relational analysis result.

2. The power settlement method based on seasonal electricity consumption characteristics according to claim 1, characterized in that Calculating the historical electricity consumption data to obtain a periodic electricity consumption sequence and an aperiodic electricity consumption sequence that fluctuate seasonally includes the following steps: Obtain meteorological data, and use the curve fitting method to fit the historical electricity consumption data with the meteorological data to obtain the relationship between electricity consumption and meteorological changes; Conduct periodic identification on the meteorological data to obtain the periodicity of the meteorological data; Screen out the periodic electricity consumption sequence and the aperiodic electricity consumption sequence from the historical electricity consumption data according to the relationship between electricity consumption and meteorological changes and the periodicity of the meteorological data.

3. The power settlement method based on seasonal electricity consumption characteristics according to claim 2, wherein Conduct feature analysis on the periodic electricity consumption sequence to obtain periodic features, including the following steps: Calculate the average value of the periodic electricity consumption sequence, and the average value is used to reflect the electricity consumption level of the season; Calculate the standard deviation of the periodic electricity consumption sequence based on the average value, and the standard deviation is used to measure the dispersion degree of the electricity consumption data within the season; Calculate the coefficient of variation of the periodic electricity consumption sequence according to the average value and the standard deviation, and the coefficient of variation is used to compare the relative magnitudes of the electricity consumption fluctuations between different seasons; Determine the periodic features of the periodic electricity consumption sequence according to the average value, the standard deviation, and the coefficient of variation.

4. The electricity settlement method based on seasonal electricity consumption characteristics according to claim 2, wherein Conduct feature analysis on the aperiodic electricity consumption sequence to obtain aperiodic features, including the following steps: Sort the aperiodic electricity consumption sequence according to the numerical size to obtain a sorted aperiodic electricity consumption sequence; Obtain the maximum value and the minimum value of the sorted aperiodic electricity consumption sequence, and calculate the range of the aperiodic electricity consumption sequence using the maximum value and the minimum value; Conduct quartile division on the sorted aperiodic electricity consumption sequence to obtain the first quartile, the second quartile, and the third quartile; Calculate the interquartile range of the aperiodic electricity consumption sequence using the first quartile and the third quartile; Determine the aperiodic features of the aperiodic electricity consumption sequence according to the range and the interquartile range.

5. The power settlement method based on seasonal electricity consumption characteristics according to claim 1, wherein Construct a deviation probability model according to the periodic features, including the following steps: Determine the statistical features of the periodic features in periodic fluctuations; Construct a periodic electricity consumption prediction model according to the statistical features; wherein, the periodic electricity consumption prediction model includes a non-trend prediction model and a trend prediction model; Construct a non-trend deviation probability model and a trend deviation probability model based on the statistical features in combination with the non-trend prediction model and the trend prediction model.

6. The electricity settlement method based on seasonal electricity consumption characteristics according to claim 1, wherein Construct a deviation probability model based on the non-periodic characteristics, including the following steps: Establish an event probability model using the non-periodic characteristics; Construct an electricity consumption prediction model according to the event probability model; Construct a power consumption prediction deviation probability model based on the event probability characteristics in combination with the electricity consumption prediction model.

7. The electricity settlement method based on seasonal electricity consumption characteristics according to claim 6, wherein Construct a power consumption prediction deviation probability model based on the event probability characteristics in combination with the electricity consumption prediction model, including the following steps: Randomly generate event samples using the event probability model; If the event sample is an occurrence sample, randomly extract a power consumption sample from the additional power consumption distribution corresponding to the event sample; Use the electricity consumption prediction model to predict the electricity consumption and obtain the periodic electricity consumption prediction value; Superimpose the power consumption sample on the periodic electricity consumption prediction value to obtain a total power consumption simulation sample; Calculate the prediction deviation between the total power consumption simulation sample and the total power consumption prediction value; Repeat the calculation process of the prediction deviation N times to obtain the statistical prediction deviation, and use the statistical prediction deviation as the probability estimate of the power consumption prediction deviation probability model.

8. A power settlement system based on seasonal electricity consumption characteristics, characterized in that Including: A data acquisition module for acquiring the historical electricity consumption data of the user within a preset time; An electricity consumption sequence calculation module for calculating the historical electricity consumption data to obtain the periodic electricity consumption sequence and non-periodic electricity consumption sequence of the historical electricity consumption data fluctuating with seasons; A feature analysis module for performing feature analysis on the periodic electricity consumption sequence and the non-periodic electricity consumption sequence to obtain periodic characteristics and non-periodic characteristics; An electricity consumption prediction module for constructing a deviation probability model according to the periodic characteristics and the non-periodic characteristics, and performing electricity consumption prediction through the deviation probability model to obtain the predicted electricity consumption; A settlement correlation analysis module for performing correlation analysis on the predicted electricity consumption by using the grey correlation analysis method, and determining the power settlement plan according to the correlation analysis result.

9. An electronic device, characterized in that, Including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, it implements the power settlement method based on seasonal electricity consumption characteristics as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the power settlement method based on seasonal electricity consumption characteristics as described in any one of claims 1 to 7.

Images