New energy equivalent output level estimation method and device

Abstract

The invention provides a new energy equivalent output level estimation method and device, and the method comprises the steps: determining an information entropy corresponding to each first time period based on the power supply information of a power system in each first time period in a historical period; determining a plurality of second time periods in the historical period based on the distribution position of the information entropy corresponding to each first time period in the historical period; for each second time period, determining an error between the equivalent output value of the new energy in the second time period and the predicted value; performing five-moment Cornish-Fisher series expansion by using the error to obtain an error random variable corresponding to the second time period; and determining a new energy equivalent output interval in the second time period based on the error random variable and the equivalent output value of the new energy in the second time period. According to the technical scheme, the new day-ahead plan can be conveniently specified by adapting to the historical output level and the historical load level of the new energy, and the electricity abandoning rate of the new energy is reduced.

Description

Technical field

[0001] The present application relates to the field of new energy technology, and in particular to a method and device for estimating the equivalent output level of new energy. [Background Technology]

[0002] With the steady advancement of my country's energy strategy, the country's renewable energy industry continues to develop. Renewable energy generation holds broad development prospects in my country's future energy landscape. Efforts will also be made to build a new power system dominated by new energy, significantly accelerating the pace of clean, low-carbon energy transition.

[0003] However, renewable energy sources such as wind power and distributed photovoltaics are subject to volatility and uncertainty, making it difficult to effectively estimate the discrepancy between their generation levels and actual load usage. This presents a significant challenge for the power system. Specifically, when renewable energy is currently involved in day-ahead planning, the resulting plans are often inaccurate and unable to adapt to actual renewable energy demand due to the uncertainty of renewable energy use at different times. This leads to unstable power supply and the risk of load loss.

[0004] Therefore, how to accurately and effectively estimate the equivalent output level of new energy to adapt to the actual demand for new energy electricity has become a technical problem that needs to be solved urgently. [Summary of the invention]

[0005] The embodiments of the present application provide a method and device for estimating the equivalent output level of new energy, aiming to solve the technical problem in related technologies that the demand for electricity from new energy is negatively affected due to the lack of accuracy in the formulation of new energy day-ahead plans.

[0006] In a first aspect, an embodiment of the present application provides a method for estimating the equivalent output level of a new energy source, including:

[0007] Determining, based on power supply information of the power system in each first period during a historical period, information entropy corresponding to each first period, wherein the power supply information includes renewable energy output or load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit in the first period;

[0008] Based on the distribution position of the information entropy corresponding to each of the first time periods in the historical period, determining a plurality of second time periods in the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different;

[0009] For each of the second time periods, determining an error between an equivalent output value of the new energy source in the second time period and a predicted value;

[0010] Performing a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second period;

[0011] Based on the error random variable and the equivalent output value of the new energy in the second time period, the new energy equivalent output range in the second time period is determined.

[0012] In one embodiment of the present application, optionally, before determining the information entropy corresponding to each first time period based on the power supply information of the power system in each first time period in a historical period, the method further includes:

[0013] Obtaining a first mean and variance of the power supply information for all first time periods in the historical period;

[0014] Among all the power supply information of the first time period in the historical period, the power supply information whose first mean and the variance meet a preset abnormal condition is deleted to obtain a valid sample set, wherein the preset abnormal condition is:

[0015]

[0016] Among them, P μ is the first mean, P σ is the variance, j is the serial number of the historical period, m is the serial number of the first period in the historical period, Represents the power supply information of the mth first time period in the jth historical period.

[0017] In one embodiment of the present application, optionally, before determining the information entropy corresponding to each first time period based on the power supply information of the power system in each first time period in a historical period, the method further includes:

[0018] Normalization is performed on the power supply information in the valid sample set.

[0019] In one embodiment of the present application, optionally, determining the information entropy corresponding to each first time period based on the power supply information of the power system in each first time period within a historical period includes:

[0020] For each first time period in the historical period, determining a net load of the power system in the first time period based on a load demand and a renewable energy output in the first time period;

[0021] Based on the Gaussian kernel function and the net load of the power system in each of the first time periods, a probability density function of the net load in each of the first time periods in the historical period is fitted, wherein:

[0022] The Gaussian kernel function is:

[0023]

[0024] Where u is a random variable;

[0025] The probability density function is:

[0026]

[0027] Wherein, m is the serial number of the first period in the historical period, K represents the Gaussian kernel function, represents the probability density of the net load of the mth first time period in the historical period, h represents the bandwidth selected for fitting, and n represents the number of first time periods in the historical period;

[0028] The information entropy corresponding to the first time period is determined based on the probability density function of the payload in the first time period and an information entropy acquisition formula, wherein the information entropy acquisition formula is:

[0029]

[0030] Among them, H m Represents the information entropy of the mth first time period in the historical period.

[0031] In one embodiment of the present application, optionally, the method further includes:

[0032] The bandwidth selected by fitting is determined based on the first standard deviation of the power supply information of each first time period in the historical period, wherein:

[0033]

[0034] h represents the bandwidth selected for fitting, n represents the number of first time periods in the historical period, and σ represents the first standard deviation.

[0035] In one embodiment of the present application, optionally, determining, for each second time period, an error between an equivalent output value of the new energy source in the second time period and a predicted value includes:

[0036] For each of the second time periods, obtaining the proportion of new energy included in the second time period;

[0037] Determine the product of the inclusion ratio of the new energy in the second period and the predicted value as the equivalent output value of the new energy in the second period;

[0038] The difference between the equivalent output value of the new energy during the second time period and the predicted value is determined as the error.

[0039] In one embodiment of the present application, optionally, performing a fifth-order Cornish-Fisher series expansion using the error to obtain the error random variable corresponding to the second time period includes:

[0040] Determine a second mean and a second standard deviation of the errors corresponding to all the second time periods;

[0041] For each of the second time periods,

[0042] Determine the third-order origin moment, the fourth-order origin moment, and the fifth-order origin moment of the error in the second time period;

[0043] Based on the second mean, the second standard deviation, the third-order origin moment, the fourth-order origin moment and the fifth-order origin moment, and the quantile of the corresponding probability of the standard Gaussian distribution, the error random variable corresponding to the second time period is determined.

[0044] In one embodiment of the present application, optionally, determining the new energy equivalent output range within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period includes:

[0045] For each second time period, determining the product of the proportion of new energy included in the second time period and the equivalent output value as the first parameter;

[0046] determining a difference between the first parameter and the error random variable as a second parameter, and determining a sum of the first parameter and the error random variable as a third parameter;

[0047] The second parameter and the third parameter are used as the upper limit and lower limit of the new energy equivalent output range within the second time period.

[0048] In a second aspect, an embodiment of the present application provides a device for estimating an equivalent output level of a new energy source, comprising:

[0049] an information entropy calculation unit, configured to determine, based on power supply information of the power system in each first time period within a historical period, an information entropy corresponding to each first time period, wherein the power supply information includes a renewable energy output or a load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit within the first time period;

[0050] a time period re-dividing unit, configured to determine a plurality of second time periods within the historical period based on a distribution position of the information entropy corresponding to each of the first time periods within the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different;

[0051] an error calculation unit, configured to determine, for each second time period, an error between an equivalent output value of the new energy source in the second time period and a predicted value;

[0052] an error random variable determining unit, configured to perform a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second time period;

[0053] The new energy equivalent output interval estimation unit is used to determine the new energy equivalent output interval within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period.

[0054] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0055] The abnormal data processing unit is configured to obtain, before determining the information entropy corresponding to each first time period, a first mean and a variance of the power supply information of all the first time periods in the historical period; and delete, from the power supply information of all the first time periods in the historical period, the power supply information whose first mean and the variance meet a preset abnormal condition, to obtain a valid sample set, wherein the preset abnormal condition is:

[0056]

[0057] Among them, P μ is the first mean, P σ is the variance, j is the serial number of the historical period, m is the serial number of the first period in the historical period, Represents the power supply information of the mth first time period in the jth historical period.

[0058] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0059] A normalization processing unit is configured to perform normalization processing on the power supply information in the valid sample set.

[0060] In one embodiment of the present application, optionally, the information entropy calculation unit includes:

[0061] a net load calculation unit, configured to determine, for each first time period in the historical period, a net load of the power system in the first time period based on a load demand and a renewable energy output in the first time period;

[0062] A probability density function calculation unit is used to fit the probability density function of the net load of each first time period in the historical period based on a Gaussian kernel function and the net load of the power system in each first time period, wherein:

[0063] The Gaussian kernel function is:

[0064]

[0065] Where u is a random variable;

[0066] The probability density function is:

[0067]

[0068] Wherein, m is the serial number of the first period in the historical period, K represents the Gaussian kernel function, represents the probability density of the net load of the mth first time period in the historical period, h represents the bandwidth selected for fitting, and n represents the number of first time periods in the historical period;

[0069] an execution unit, configured to determine the information entropy corresponding to the first time period based on a probability density function of the payload in the first time period and an information entropy acquisition formula, wherein the information entropy acquisition formula is:

[0070]

[0071] Among them, H m Represents the information entropy of the mth first time period in the historical period.

[0072] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0073] A fitting bandwidth determination unit is configured to determine the bandwidth selected for fitting based on a first standard deviation of the power supply information of each of the first time periods in the historical cycle, wherein:

[0074]

[0075] h represents the bandwidth selected for fitting, n represents the number of first time periods in the historical period, and σ represents the first standard deviation.

[0076] In one embodiment of the present application, optionally, the error calculation unit is configured to:

[0077] For each of the second time periods, obtain the proportion of new energy included in the second time period; determine the product of the proportion of new energy included in the second time period and the predicted value as the equivalent output value of the new energy in the second time period; determine the difference between the equivalent output value of the new energy in the second time period and the predicted value as the error.

[0078] In one embodiment of the present application, optionally, the error random variable determination unit is configured to:

[0079] Determine the second mean and second standard deviation of the error corresponding to all the second time periods; for each second time period, determine the third-order origin moment, fourth-order origin moment and fifth-order origin moment of the error in the second time period; based on the second mean, the second standard deviation, the third-order origin moment, the fourth-order origin moment and the fifth-order origin moment, and the quantile of the corresponding probability of the standard Gaussian distribution, determine the error random variable corresponding to the second time period.

[0080] In one embodiment of the present application, optionally, the new energy equivalent output interval estimation unit is configured to:

[0081] For each of the second time periods, the product of the proportion of new energy inclusion in the second time period and the equivalent output value is determined as a first parameter; the difference between the first parameter and the error random variable is determined as a second parameter, and the sum of the first parameter and the error random variable is determined as a third parameter; the second parameter and the third parameter are used as the upper limit and lower limit of the new energy equivalent output range in the second time period.

[0082] In a third aspect, an embodiment of the present application provides a computer device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the method described in the first aspect above.

[0083] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method described in the first aspect above.

[0084] The above technical solution addresses the technical problem in related technologies where the lack of accuracy in the formulation of day-ahead plans for new energy sources negatively impacts the electricity demand for new energy sources. It provides a new day-ahead plan estimation method for the power system. It can re-divide the estimated new energy equivalent output level into more regular time periods based on the distribution of information entropy in different time periods within the historical cycle, thereby accurately estimating the error between the equivalent output value of new energy sources and the predicted value according to the time period, and performing a fifth-order moment Cornish-Fisher series expansion based on the error to obtain the new energy equivalent output range. As a result, the accuracy of the estimation of the equivalent output level of new energy sources is improved, the error in the calculation process is reduced, and it is easier to specify a new day-ahead plan based on the historical output level and historical load level of new energy sources, thereby improving the adaptability of new energy output to electricity demand, reducing the power curtailment rate of new energy sources, and rationally arranging the use cost of the power system.

Brief Description of the Drawings

[0085] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0086] Figure 1 A flowchart of a method for estimating a new energy equivalent output level according to an embodiment of the present application is shown;

[0087] Figure 2 A schematic diagram of information entropy distribution according to an embodiment of the present application is shown;

[0088] Figure 3 A flow chart showing a method for estimating a new energy equivalent output level according to another embodiment of the present application is shown;

[0089] Figure 4 A schematic diagram showing the proportion of new energy sources incorporated according to an embodiment of the present application is shown;

[0090] Figure 5 A schematic diagram showing equivalent output of new energy sources according to an embodiment of the present application is shown;

[0091] Figure 6 A schematic diagram showing equivalent output of new energy at an 85% confidence level according to an embodiment of the present application is shown;

[0092] Figure 7 A schematic diagram showing equivalent output of new energy at a 95% confidence level according to an embodiment of the present application is shown;

[0093] Figure 8A block diagram of a computer device according to an embodiment of the present application is shown;

[0094] Figure 9 A block diagram of a computer device according to another embodiment of the present application is shown. [Specific implementation method]

[0095] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0096] Figure 1 A flow chart of a method for estimating a new energy equivalent output level according to an embodiment of the present application is shown.

[0097] like Figure 1 As shown, a new energy equivalent output level estimation method according to an embodiment of the present application includes:

[0098] Step 102: Based on the power supply information of the power system in each first time period during a historical period, determine the information entropy corresponding to each first time period, wherein the power supply information includes the output of new energy or the load demand, and the information entropy is used to reflect the uncertainty of the output level of the new energy unit in the first time period.

[0099] The historical cycle described in this plan refers to the time interval of the historical day-ahead plan formulated for the power system. During each first period of the historical cycle, the new energy units are in power supply, or the loads powered by new energy are in power consumption.

[0100] Therefore, this power supply information reflects the historical level of renewable energy in the power system, or the historical level of demand for renewable energy from the load. While this power supply information reflects the actual output of renewable energy units, it can also reflect the uncertainty of their output levels. Information entropy is an indicator of the degree of information confusion regarding renewable energy unit output levels.

[0101] Step 104: Based on the distribution position of the information entropy corresponding to each of the first time periods in the historical period, multiple second time periods are determined in the historical period, wherein multiple information entropies are distributed in each of the multiple second time periods, and the information entropy fluctuation levels of the multiple second time periods are different.

[0102] In a possible design, the distribution position of the information entropy corresponding to each of the first time periods in the historical period is as follows: Figure 2 As shown, Figure 2 The information entropy in the data is clearly divided into three parts in different time periods, and the information entropy fluctuation levels of the three parts are small volatility, large volatility and maximum volatility. Figure 2 In the actual scenario shown, the data of the day can be divided into three parts: high uncertainty period (10:00-16:00), medium uncertainty period (16:15-22:00) and low uncertainty period (other periods).

[0103] Therefore, the re-divided time period is based on the uncertainty of the output level of the new energy units, or in other words, the re-divided time period shows the law of the output of the new energy units. The equivalent output value of new energy in this period can more accurately and effectively show the actual situation of the output of the new energy units.

[0104] Step 106: for each second time period, determine the error between the equivalent output value of the new energy in the second time period and the predicted value.

[0105] Based on the re-divided time periods, the error between the equivalent output value of new energy and the predicted value can be calculated more accurately, reducing the noise of the error, thereby improving the accuracy of the estimation of the equivalent output level of new energy in subsequent calculations.

[0106] Step 108: Perform a fifth-order Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second time period.

[0107] Step 110 : determining the new energy equivalent output range within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period.

[0108] Finally, the fifth-order moment Cornish-Fisher series expansion method is used to further estimate the error random variable corresponding to the re-divided time period, and the range of the equivalent output value within the re-divided time period through the variation of the error random variable is taken as the new energy equivalent output range of the time period.

[0109] The above technical solution provides a new method for estimating day-ahead plans for power systems. It can re-divide the estimated renewable energy equivalent output level into more regular time periods based on the distribution of information entropy at different time periods within the historical cycle, thereby accurately estimating the error between the renewable energy equivalent output value and the predicted value according to the time period. Based on this error, a fifth-order Cornish-Fisher series expansion is performed to obtain the renewable energy equivalent output range. This improves the accuracy of the estimation of renewable energy equivalent output levels, reduces errors in the calculation process, facilitates the designation of new day-ahead plans based on the historical output levels and historical load levels of renewable energy, improves the adaptability of renewable energy output to electricity demand, reduces the curtailment rate of renewable energy, and rationally arranges the use cost of the power system.

[0110] In a possible design, before determining the information entropy corresponding to each of the first time periods, abnormal information in the power supply information of the power system in each first time period within the historical period can be identified and eliminated to improve the reliability of the sample data.

[0111] Specifically, the first mean value P of the power supply information of all the first time periods in the historical period can be obtained. μ and variance P σ :

[0112]

[0113] Wherein, j is the serial number of the historical period, k is the total number of the historical periods, and m is the serial number of the first period in the historical period. represents the power supply information of the mth first time period in the jth historical period. Optionally, the historical period is 24 hours, including 96 first time periods in total, and the duration of each first time period is 15 minutes.

[0114] Next, from the power supply information of all the first time periods in the historical period, the power supply information whose first mean and the variance meet a preset abnormal condition is deleted to obtain a valid sample set, wherein the preset abnormal condition is:

[0115]

[0116] Among them, P μ is the first mean, P σ is the variance, j is the serial number of the historical period, m is the serial number of the first period in the historical period, Represents the power supply information of the mth first time period in the jth historical period.

[0117] In one possible design, to further improve the reliability of sample data and reduce the impact of magnitude differences between data on the accuracy of calculation results, the power supply information in the valid sample set may be normalized after deleting abnormal data:

[0118]

[0119] in, express The normalized value, x min Indicates the minimum value of new energy output or load demand in the month of the historical cycle, x max Indicates the maximum value of renewable energy output or load demand in the month of the historical period.

[0120] Figure 3 A flow chart of a new energy equivalent output level estimation method according to another embodiment of the present application is shown.

[0121] like Figure 3 As shown, according to another embodiment of the present application, a method for estimating the equivalent output level of new energy includes:

[0122] Step 302: For each first time period in the historical period, determine the net load of the power system in the first time period based on the load demand and the new energy output in the first time period.

[0123] Net load represents the required output of conventional generators in a power system. The greater the net load at a given moment, the higher the required output of conventional generators. Net load size is not only related to load demand but also influenced by wind and photovoltaic output. Because both the source and the load are subject to uncertainty, it is necessary to account for this uncertainty in day-ahead scheduling to avoid grid operational risks.

[0124] In one possible design, the net load of the power system in the first period of the mth historical period is calculated as follows:

[0125]

[0126] in, represents the net load of the power system in the first period of the mth historical period, represents the load demand in the first period of the mth period in the historical period, represents the actual value of wind power output in the first period of the mth period in the historical period, Indicates the actual value of the photovoltaic output in the first period of the mth period in the historical period.

[0127] Step 304 : Fitting a probability density function of the net load in each of the first time periods in the historical period based on a Gaussian kernel function and the net load of the power system in each of the first time periods.

[0128] Wherein, the Gaussian kernel function is:

[0129]

[0130] Where u is a random variable.

[0131] Wherein, the probability density function is:

[0132]

[0133] Wherein, m is the serial number of the first period in the historical period, K represents the Gaussian kernel function, represents the probability density of the net load in the mth first time period in the historical period, h represents the bandwidth selected for fitting, and n represents the number of first time periods in the historical period.

[0134] Specifically, after calculating the net load at each first moment, the Gaussian kernel function density estimation method is used to count the net load sizes at different moments and fit their distribution to obtain the net load probability distribution, that is, the probability density function.

[0135] The selection of bandwidth h will greatly affect the fitting effect of the kernel density estimation algorithm. If the selected bandwidth value h is too small, the resulting probability density function will contain more noise, and the fitting result will be less smooth. If it is too large, the resulting probability density function will be too smooth, and some features of the original sequence may be obscured, resulting in large deviations. To this end, the bandwidth selected for fitting can be determined based on the first standard deviation of the power supply information in each first time period in the historical cycle to obtain the optimal bandwidth:

[0136]

[0137] Wherein, h represents the bandwidth selected for fitting, n represents the number of first time periods in the historical period, and σ represents the first standard deviation.

[0138] The kernel density estimation method is used to fit the net load probability distribution of the power system in each first period in the data set. Since there is no need to assume in advance what distribution the sample obeys, the fitting effect of this application is more accurate compared to the conventional Gaussian distribution and t distribution.

[0139] Step 306: Determine the information entropy corresponding to the first time period based on the probability density function of the net load in the first time period and the information entropy acquisition formula.

[0140] Information entropy is a metric that measures the degree of information chaos. The magnitude of information entropy reflects the amount of information in a set of random variables. A greater amount of information in the data indicates greater variability among the possible outcomes; in other words, a greater entropy indicates greater uncertainty in the random variable. Conversely, a lower entropy indicates less uncertainty in the random variable. This paper measures the uncertainty of load or new energy sources by calculating the information entropy of net loads at different time periods.

[0141] The information entropy acquisition formula is:

[0142]

[0143] Among them, H m Represents the information entropy of the mth first time period in the historical period.

[0144] Step 308: Based on the distribution position of the information entropy corresponding to each of the first time periods in the historical period, multiple second time periods are determined in the historical period, wherein multiple information entropies are distributed in each of the multiple second time periods, and the information entropy fluctuation levels of the multiple second time periods are different.

[0145] Based on the distribution of information entropy at different times, the data within a single period is divided into three parts: high uncertainty period, medium uncertainty period and low uncertainty period. The corresponding loss load risk probability is set for different periods in turn.

[0146] Step 310: For each second time period, obtain the proportion of new energy output included in the second time period.

[0147] Step 312: Determine the product of the inclusion ratio of the new energy output in the second period and the predicted value as the equivalent output value of the new energy in the second period.

[0148] Specifically, first, the constraints for the power system to avoid load loss are determined as follows:

[0149]

[0150] This constraint can be transformed into:

[0151]

[0152] Among them, P rob (·) represents the probability of an event occurring, α represents the probability of the power system experiencing a load loss risk, and They represent the predicted value of load demand, wind power output, and photovoltaic power output of the power system in the second period of the i-th historical cycle, respectively. They represent the actual value of the load demand of the power system, the actual value of wind power output, and the actual value of photovoltaic power output in the second period of the i-th historical cycle, respectively. w P is the proportion of wind power output participating in the day-ahead balance, λ p It refers to the proportion of photovoltaic power generation output included in the day-ahead balance.

[0153] Furthermore, the output P of the new energy unit in the second period of the i-th historical cycle is G,i and the net load of the power system in the second period of the i-th period in the historical cycle The calculation methods are:

[0154]

[0155] remember Based on the definition of the probability distribution function, the constraints are further processed to obtain:

[0156]

[0157] Among them, F W is the probability distribution function of W.

[0158] Furthermore, the inclusion ratio of wind power output in the second period of the i-th historical cycle when participating in the day-ahead balance can be determined as:

[0159]

[0160] Among them, here Equivalent to Equivalent to The calculation method of photovoltaic power generation output is the same, which will not be repeated here. Optionally, the changes in the proportion of wind power and photovoltaic power generation over time are as follows: Figure 4 shown.

[0161] Furthermore, the probabilistic equivalent output of new energy within a unit period can be determined as:

[0162]

[0163] Among them, P w,t and P pv,t Respectively represent the equivalent output values ​​of wind power generation and photovoltaic power generation in time period t, λ w,t and λ pv,t They represent the proportion of wind power generation and photovoltaic power generation included in time period t, P pre,w,t and P pre,pv,t Respectively represent the predicted values ​​of wind power generation and photovoltaic power generation in time period t. Figure 5As shown in the figure, the predicted value, actual value and equivalent output value of new energy have obvious differences in the change patterns over time between different days.

[0164] Step 314: Determine the difference between the equivalent output value of the new energy source during the second period and the predicted value as the error:

[0165]

[0166] in, represents the error of the kth sample information in the tth second period, i.e., the power supply information, and They represent the equivalent output value and predicted value of the corresponding new energy respectively.

[0167] Step 316: Determine the second mean and the second standard deviation of the error corresponding to all the second time periods. For each second time period, determine the third-order origin moment, the fourth-order origin moment, and the fifth-order origin moment of the error in the second time period.

[0168] Step 318: Determine the error random variable corresponding to the second time period based on the second mean, the second standard deviation, the third-order origin moment, the fourth-order origin moment, the fifth-order origin moment, and the quantile of the corresponding probability of the standard Gaussian distribution.

[0169] Using the Cornish-Fisher series with 5th-order moments, the probability distribution of the forecast error of new energy in different time periods is established, and the error random variable τ quantile of is calculated as follows:

[0170]

[0171]

[0172]

[0173]

[0174]

[0175]

[0176] Among them, J t represents the total number of samples in the t-th second period, η t and σ t Represent the mean and standard deviation of the forecast error in the t-th second period, u t,3 、u t,4 、u t,5They represent the 3rd, 4th and 5th order origin moments of the new energy forecast error in the tth second period, ξ τ Represents the quantile of the standard Gaussian distribution corresponding to probability τ.

[0177] The Cornish-Fisher series expansion method constructs the forecast error origin moments through the above process and obtains the quantiles of the forecast error CDF. It has a good fitting effect on non-normal distributions with obvious eccentricity and can directly fit the quantiles of the forecast error CDF representing the confidence interval. Compared with methods such as kernel density estimation, it omits the step of inverting the CDF to indirectly obtain the quantiles, making it simpler to operate.

[0178] Step 320: Determine the new energy equivalent output range within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period.

[0179] Specifically, for each second time period, the product of the proportion of new energy included in the second time period and the equivalent output value is determined as the first parameter; the difference between the first parameter and the error random variable is determined as the second parameter, and the sum of the first parameter and the error random variable is determined as the third parameter; the second parameter and the third parameter are used as the upper and lower limits of the new energy equivalent output range in the second time period. That is:

[0180]

[0181] Among them, P upper and P lower They represent the upper and lower limits of the equivalent output range of new energy in the t-th second period, λ t Indicates the proportion of new energy included, P pre,t It represents the equivalent output value of the new energy in the t-th second period.

[0182] In one possible design, Figure 6 and Figure 7 As shown, the equivalent output of the new energy is calculated at confidence levels of 85% and 95%, respectively. Specifically, after dividing the second time period into multiple periods, the error is calculated, and the probability distribution of the error is determined by the Cornish-Fisher series expansion method. Furthermore, according to the given confidence level τ, the shortest interval that meets the requirements is found, and it is used as the confidence interval of the error, and the equivalent output of the new energy is further calculated to obtain the output value of the new energy at the specified confidence level. Among them, the output value of the new energy at the specified confidence level can be selected as the product of its equivalent output value and the confidence level.

[0183] Through the above steps, the equivalent output of renewable energy at a specified confidence level can be determined. When formulating day-ahead plans, high-uncertainty periods are calculated according to the lower limit of renewable energy equivalent output, which can effectively reduce the operating risk of the power system. At the same time, low-uncertainty periods are calculated according to the upper limit of renewable energy equivalent output, which can reduce the renewable energy curtailment rate while minimizing the risk.

[0184] According to one embodiment of the present application, a new energy equivalent output level estimation device includes:

[0185] an information entropy calculation unit, configured to determine, based on power supply information of the power system in each first time period within a historical period, an information entropy corresponding to each first time period, wherein the power supply information includes a renewable energy output or a load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit within the first time period;

[0186] a time period re-dividing unit, configured to determine a plurality of second time periods within the historical period based on a distribution position of the information entropy corresponding to each of the first time periods within the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different;

[0187] an error calculation unit, configured to determine, for each second time period, an error between an equivalent output value of the new energy source in the second time period and a predicted value;

[0188] an error random variable determining unit, configured to perform a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second time period;

[0189] The new energy equivalent output interval estimation unit is used to determine the new energy equivalent output interval within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period.

[0190] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0191] The abnormal data processing unit is configured to obtain, before determining the information entropy corresponding to each first time period, a first mean and a variance of the power supply information of all the first time periods in the historical period; and delete, from the power supply information of all the first time periods in the historical period, the power supply information whose first mean and the variance meet a preset abnormal condition, to obtain a valid sample set, wherein the preset abnormal condition is:

[0192]

[0193] Among them, Pμ is the first mean, P σ is the variance, j is the serial number of the historical period, m is the serial number of the first period in the historical period, Represents the power supply information of the mth first time period in the jth historical period.

[0194] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0195] A normalization processing unit is configured to perform normalization processing on the power supply information in the valid sample set.

[0196] In one embodiment of the present application, optionally, the information entropy calculation unit includes:

[0197] a net load calculation unit, configured to determine, for each first time period in the historical period, a net load of the power system in the first time period based on a load demand and a renewable energy output in the first time period;

[0198] A probability density function calculation unit is used to fit the probability density function of the net load of each first time period in the historical period based on a Gaussian kernel function and the net load of the power system in each first time period, wherein:

[0199] The Gaussian kernel function is:

[0200]

[0201] Where u is a random variable;

[0202] The probability density function is:

[0203]

[0204] Wherein, m is the serial number of the first period in the historical period, K represents the Gaussian kernel function, represents the probability density of the net load of the mth first time period in the historical period, h represents the bandwidth selected for fitting, and n represents the number of first time periods in the historical period;

[0205] an execution unit, configured to determine the information entropy corresponding to the first time period based on a probability density function of the payload in the first time period and an information entropy acquisition formula, wherein the information entropy acquisition formula is:

[0206]

[0207] Among them, H m Represents the information entropy of the mth first time period in the historical period.

[0208] In one embodiment of the present application, optionally, the new energy equivalent output level estimation device further includes:

[0209] A fitting bandwidth determination unit is configured to determine the bandwidth selected for fitting based on a first standard deviation of the power supply information of each of the first time periods in the historical cycle, wherein:

[0210]

[0211] h represents the bandwidth selected for fitting, n represents the number of first time periods in the historical period, and σ represents the first standard deviation.

[0212] In one embodiment of the present application, optionally, the error calculation unit is configured to:

[0213] For each of the second time periods, obtain the proportion of new energy included in the second time period; determine the product of the proportion of new energy included in the second time period and the predicted value as the equivalent output value of the new energy in the second time period; determine the difference between the equivalent output value of the new energy in the second time period and the predicted value as the error.

[0214] In one embodiment of the present application, optionally, the error random variable determination unit is configured to:

[0215] Determine the second mean and second standard deviation of the error corresponding to all the second time periods; for each second time period, determine the third-order origin moment, fourth-order origin moment and fifth-order origin moment of the error in the second time period; based on the second mean, the second standard deviation, the third-order origin moment, the fourth-order origin moment and the fifth-order origin moment, and the quantile of the corresponding probability of the standard Gaussian distribution, determine the error random variable corresponding to the second time period.

[0216] In one embodiment of the present application, optionally, the new energy equivalent output interval estimation unit is configured to:

[0217] For each of the second time periods, the product of the proportion of new energy inclusion in the second time period and the equivalent output value is determined as a first parameter; the difference between the first parameter and the error random variable is determined as a second parameter, and the sum of the first parameter and the error random variable is determined as a third parameter; the second parameter and the third parameter are used as the upper limit and lower limit of the new energy equivalent output range in the second time period.

[0218] The new energy equivalent output level estimation device uses any one of the solutions described in the above embodiments, and therefore has all the above technical effects, which will not be repeated here.

[0219] In addition, in one embodiment, the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, network interface and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it can implement the method described in any of the above embodiments.

[0220] In one embodiment, the present application further provides a computer device, which may be a client, and its internal structure diagram may be as follows: Figure 9 As shown. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When executed by the processor, the computer program can implement the method described in any of the above embodiments.

[0221] Any of the aforementioned computer devices in the embodiments of the present application may exist in various forms, including but not limited to:

[0222] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily provide voice and data communications. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0223] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0224] (3) Portable entertainment devices: These devices can display and play multimedia content. These devices include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys, wearable devices, and portable car navigation devices.

[0225] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0226] (5) Other electronic devices with data interaction functions.

[0227] In addition, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to perform the following steps:

[0228] Determining, based on power supply information of the power system in each first period during a historical period, information entropy corresponding to each first period, wherein the power supply information includes renewable energy output or load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit in the first period;

[0229] Based on the distribution position of the information entropy corresponding to each of the first time periods in the historical period, determining a plurality of second time periods in the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different;

[0230] For each of the second time periods, determining an error between an equivalent output value of the new energy source in the second time period and a predicted value;

[0231] Performing a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second period;

[0232] Based on the error random variable and the equivalent output value of the new energy in the second time period, the new energy equivalent output range in the second time period is determined.

[0233] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0234] The above describes the technical solution of the present application in detail in conjunction with the accompanying drawings. Through the technical solution of the present application, a new day-ahead plan estimation method is provided for the power system. It can re-divide the time period into more regular periods for estimating the equivalent output level of new energy through the distribution of information entropy in different time periods within the historical cycle, thereby accurately estimating the error between the equivalent output value of new energy and the predicted value according to the time period, and perform a 5th-order moment Cornish-Fisher series expansion based on the error to obtain the equivalent output range of new energy. As a result, the accuracy of the estimation of the equivalent output level of new energy is improved, the error in the calculation process is reduced, and it is convenient to adapt to the historical output level and historical load level of new energy to specify a new day-ahead plan, improve the adaptability of new energy output and electricity demand, reduce the power abandonment rate of new energy, and reasonably arrange the use cost of the power system.

[0235] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0236] The terms used in the embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "an", "the" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0237] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of the device or unit, which may be electrical, mechanical or other forms.

[0238] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0239] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0240] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for estimating the equivalent output level of new energy, characterized in that: include: Determining, based on power supply information of the power system in each first period during a historical period, information entropy corresponding to each first period, wherein the power supply information includes renewable energy output or load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit in the first period; Based on the distribution position of the information entropy corresponding to each of the first time periods in the historical period, determining a plurality of second time periods in the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different; For each of the second time periods, determining an error between an equivalent output value of the new energy source in the second time period and a predicted value; Performing a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second period; Based on the error random variable and the equivalent output value of the new energy in the second time period, the new energy equivalent output range in the second time period is determined.

2. The new energy equivalent output level estimation method according to claim 1, characterized in that: Before determining the information entropy corresponding to each first time period based on the power supply information of the power system in each first time period in the historical period, the method further includes: Obtaining a first mean and variance of the power supply information for all first time periods in the historical period; Among all the power supply information of the first time period in the historical period, the power supply information whose first mean and the variance meet a preset abnormal condition is deleted to obtain a valid sample set, wherein the preset abnormal condition is: Among them, P μ is the first mean, P σ is the variance, j is the serial number of the historical period, m is the serial number of the first period in the historical period, Represents the power supply information of the mth first time period in the jth historical period.

3. The new energy equivalent output level estimation method according to claim 2, characterized in that: Before determining the information entropy corresponding to each first time period based on the power supply information of the power system in each first time period in the historical period, the method further includes: Normalization is performed on the power supply information in the valid sample set.

4. The method for estimating the equivalent output level of new energy according to any one of claims 1 to 3, characterized in that: The determining, based on the power supply information of each first time period of the power system in the historical period, the information entropy corresponding to each first time period includes: For each first time period in the historical period, determining a net load of the power system in the first time period based on a load demand and a renewable energy output in the first time period; Based on the Gaussian kernel function and the net load of the power system in each of the first time periods, a probability density function of the net load in each of the first time periods in the historical period is fitted, wherein: The Gaussian kernel function is: Where u is a random variable; The probability density function is: Wherein, m is the serial number of the first period in the historical period, K represents the Gaussian kernel function, represents the probability density of the net load of the mth first time period in the historical period, h represents the bandwidth selected for fitting, and n represents the number of first time periods in the historical period; The information entropy corresponding to the first time period is determined based on the probability density function of the payload in the first time period and an information entropy acquisition formula, wherein the information entropy acquisition formula is: Among them, H m Represents the information entropy of the mth first time period in the historical period.

5. The new energy equivalent output level estimation method according to claim 4, characterized in that: Also includes: The bandwidth selected by fitting is determined based on the first standard deviation of the power supply information of each first time period in the historical period, wherein: h represents the bandwidth selected for fitting, n represents the number of first time periods in the historical period, and σ represents the first standard deviation.

6. The new energy equivalent output level estimation method according to claim 4, characterized in that: The determining, for each second time period, an error between an equivalent output value of the new energy source in the second time period and a predicted value includes: For each of the second time periods, obtaining the proportion of new energy included in the second time period; Determine the product of the inclusion ratio of the new energy in the second period and the predicted value as the equivalent output value of the new energy in the second period; The difference between the equivalent output value of the new energy during the second time period and the predicted value is determined as the error.

7. The new energy equivalent output level estimation method according to claim 6, characterized in that: The step of performing a fifth-order Cornish-Fisher series expansion on the error to obtain an error random variable corresponding to the second time period includes: Determine a second mean and a second standard deviation of the errors corresponding to all the second time periods; For each of the second time periods, Determine the third-order origin moment, the fourth-order origin moment, and the fifth-order origin moment of the error in the second time period; Based on the second mean, the second standard deviation, the third-order origin moment, the fourth-order origin moment and the fifth-order origin moment, and the quantile of the corresponding probability of the standard Gaussian distribution, the error random variable corresponding to the second time period is determined.

8. The new energy equivalent output level estimation method according to claim 7, characterized in that: The determining, based on the error random variable and the equivalent output value of the new energy in the second time period, the new energy equivalent output range in the second time period includes: For each second time period, determining the product of the proportion of new energy included in the second time period and the equivalent output value as the first parameter; determining a difference between the first parameter and the error random variable as a second parameter, and determining a sum of the first parameter and the error random variable as a third parameter; The second parameter and the third parameter are used as the upper limit and lower limit of the new energy equivalent output range within the second time period.

9. A device for estimating equivalent output level of new energy, characterized in that: include: an information entropy calculation unit, configured to determine, based on power supply information of the power system in each first time period within a historical period, an information entropy corresponding to each first time period, wherein the power supply information includes a renewable energy output or a load demand, and the information entropy is used to reflect the uncertainty of the output level of the renewable energy unit within the first time period; a time period re-dividing unit, configured to determine a plurality of second time periods within the historical period based on a distribution position of the information entropy corresponding to each of the first time periods within the historical period, wherein a plurality of the information entropies are distributed in each of the plurality of second time periods, and the information entropy fluctuation levels of the plurality of second time periods are different; an error calculation unit, configured to determine, for each second time period, an error between an equivalent output value of the new energy source in the second time period and a predicted value; an error random variable determining unit, configured to perform a fifth-order moment Cornish-Fisher series expansion using the error to obtain an error random variable corresponding to the second time period; The new energy equivalent output interval estimation unit is used to determine the new energy equivalent output interval within the second time period based on the error random variable and the equivalent output value of the new energy within the second time period.

10. A computer-readable storage medium, characterized in that Computer-executable instructions are stored, and the computer-executable instructions are used to execute the method according to any one of claims 1 to 8.

Images