New energy characteristic evaluation method and system based on distance-horizontal analysis

Abstract

The invention discloses a new energy characteristic evaluation method and system based on distance-horizontal analysis, and the method comprises the steps: collecting the data of a historical new energy wind-light output actual value and a wind-light daily power generation actual value, and carrying out the preprocessing of the data; converting the preprocessed historical new energy wind and light output actual value and wind and light daily power generation actual value sequence into a distance-average sequence, an accumulated distance-average sequence and a standard power generation index sequence; and based on the distance-average sequence, the accumulated distance-average sequence and the standard power generation index sequence, evaluating the new energy characteristics of the target area by applying a distance-average analysis method to obtain a new energy characteristic evaluation result. Based on the current development situation that high-proportion new energy is connected to a power system, and aiming at the defects of an existing new energy characteristic evaluation method, a distance-horizontal analysis method in the meteorological field is introduced into new energy characteristic evaluation, so that new energy characteristics are further known, the advantages of the new energy are better played, and the new energy characteristic evaluation method has a good application prospect. And a foundation is laid for researching planning and operation problems of a high-proportion new energy power system.

Description

Technical Field

[0001] This invention belongs to the field of power system new energy characteristic analysis, specifically involving a new energy characteristic evaluation method and system based on anomaly analysis. Background Technology

[0002] The new power system, primarily based on new energy sources such as wind and solar power, is an important component of the new energy system. However, the output of wind and solar power is highly dependent on weather conditions, exhibiting strong randomness and intermittency, posing a serious challenge to the safe operation of the power system.

[0003] In the field of new energy characteristic research, existing research mainly focuses on the analysis of randomness and intermittency. Conventional statistical indicators such as mean, extreme values, and typical power output curves have formed a basic cognitive system. Regarding randomness, the Weibull distribution, Rayleigh distribution, and log-normal distribution have been used to fit the probability distribution of wind speed; some literature has also proposed using the Beta distribution to fit the wind power output distribution and using the Beta distribution to fit the wind power prediction error, and using indicators such as average relative error, average absolute error, and root mean square error to evaluate the prediction error. Regarding volatility, domestic and foreign scholars have defined hourly power change indicators for wind power to analyze the volatility characteristics of wind power, using the t-distribution with shift factor and scaling factor and the Gaussian mixture model to fit the rate of change of wind power, and using volatility indicators and ramp rate indicators to construct an evaluation system that takes into account both random volatility and continuous ramping.

[0004] In the field of meteorology, assessment indicators such as anomalies, cumulative anomalies, and standard precipitation indices have been established for traditional meteorological elements such as precipitation and temperature. Relatively systematic and mature methods for analyzing extreme meteorological events have also been developed and widely applied in climate monitoring and diagnosis, meteorological disaster assessment, and climate change research, achieving good analytical results for extreme meteorological disasters such as droughts, floods, cold waves, and heat waves. However, related anomaly analysis methods have not yet been systematically applied in the analysis of new energy characteristics. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for evaluating the characteristics of new energy sources based on anomaly analysis. It is based on the current development status of high-proportion new energy sources being integrated into the power system, and addresses the shortcomings of existing new energy characteristic evaluation methods by introducing anomaly analysis methods from the meteorological field into the evaluation of new energy characteristics. This will help to further understand the characteristics of new energy sources, better leverage their advantages, and lay the foundation for studying the planning and operation of high-proportion new energy power systems.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A new energy characteristic evaluation method based on anomaly analysis includes: Step 1: Collect historical data on actual output of wind and solar power and actual daily power generation of wind and solar energy, and preprocess the data; Step 2: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into anomaly sequences; Step 3: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a cumulative anomaly sequence; Step 4: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a standard power generation index sequence; Step 5: Based on the anomaly sequence, cumulative anomaly sequence, and standard power generation index sequence, apply the anomaly analysis method to evaluate the new energy characteristics of the target area and obtain the new energy characteristic evaluation results.

[0007] A further improvement of this invention is that, in step two, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into an anomaly sequence, wherein the anomaly definition formula for new energy sources is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n The total time for the selected reference period; a positive anomaly indicates that the power and electricity consumption at that time are above the average level, while a negative anomaly indicates that they are below the average level; Anomalies are derived according to different dimensions: according to time scale, they are divided into intraday, intramonth, intrayear, and interannual anomalies; according to spatial scale, they are divided into single-machine, field cluster, regional, and system anomalies; and according to statistical methods, they are divided into anomaly probability distribution, maximum positive / negative anomaly, and anomaly percentage.

[0008] A further improvement of this invention lies in that, in step three, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are transformed into a cumulative anomaly sequence. The cumulative anomaly is a time series obtained by successively accumulating the anomaly sequence in chronological order, defined as... (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time of day, which is 0 at 0:00; When new energy data is higher than the average, the positive anomaly accumulates and causes the curve to rise, reflecting a "surplus" state; when new energy data is lower than the average, the negative anomaly accumulates and causes the curve to fall, reflecting a "deficit" state; if the curve shows frequent alternation between rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state. The slope of the curve depicts the rate of change of the cumulative anomaly; a positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus; a negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit. On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase; the maximum point represents the highest peak of historical cumulative surplus; conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase.

[0009] A further improvement of this invention is that, in step four, the preprocessed historical actual values ​​of wind and solar power output and actual daily power generation of wind and solar are converted into a standard power generation index sequence. The standard power generation index is used to measure the abnormal level of new energy power and electricity data. While intuitively reflecting whether new energy is too much or too little, the standard power generation index eliminates the absolute value difference caused by regional differences or different statistical scales, so that various power generation anomalies can be compared across time and space under a unified scale. The conversion process of the standard power generation index includes: first, fitting the probability distribution of the historical power and electricity series to construct its cumulative distribution function, and then mapping the cumulative probability to the standard normal distribution to obtain the Z-score series with a mean of 0 and a standard deviation of 1, thereby achieving the standardization of the series.

[0010] A further improvement of this invention is that the specific calculation process for the standard power generation index is as follows: Data preprocessing: Collect new energy power and power data for the target area; imput and correct missing or outlier values ​​to ensure the integrity and consistency of the sample; Kernel density estimation: By selecting a suitable kernel function and bandwidth parameters, kernel density estimation is performed on historical power and electricity data to construct a probability density function. ; Construction of the cumulative distribution function: Using numerical integration methods, the probability density function is... Integrating over the interval of the independent variable yields the cumulative distribution function. : (3) And normalize it to ensure ; Standard normal distribution mapping: mapping the cumulative distribution function The quantiles mapped to the standard normal distribution are used as the standardization index, with their corresponding Z-values: (4) Its distribution approximately follows a normal distribution with a mean of 0 and a standard deviation of 1, quantifying the degree of deviation of the current value from the historical average level and distribution characteristics.

[0011] A new energy characteristic evaluation system based on anomaly analysis includes: The data collection and preprocessing unit collects historical data on actual output of new energy wind and solar power and actual daily power generation of wind and solar power, and preprocesses the data. The first data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into anomaly sequences. The second data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a cumulative anomaly sequence. The third data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a standard power generation index sequence. The evaluation unit, based on the anomaly sequence, cumulative anomaly sequence, and standard power generation index sequence, applies anomaly analysis to evaluate the new energy characteristics of the target area and obtains the new energy characteristic evaluation results.

[0012] A further improvement of this invention is that, in the first data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into an anomaly sequence, wherein the definition formula for the anomaly of new energy sources is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n The total time for the selected reference period; a positive anomaly indicates that the power and electricity consumption at that time are above the average level, while a negative anomaly indicates that they are below the average level; Anomalies are derived according to different dimensions: according to time scale, they are divided into intraday, intramonth, intrayear, and interannual anomalies; according to spatial scale, they are divided into single-machine, field cluster, regional, and system anomalies; and according to statistical methods, they are divided into anomaly probability distribution, maximum positive / negative anomaly, and anomaly percentage.

[0013] A further improvement of this invention lies in that, in the second data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into a cumulative anomaly sequence. The cumulative anomaly is a time series obtained by successively accumulating the anomaly sequence in chronological order, defined as... (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time of day, which is 0 at 0:00; When new energy data is higher than the average, the positive anomaly accumulates and causes the curve to rise, reflecting a "surplus" state; when new energy data is lower than the average, the negative anomaly accumulates and causes the curve to fall, reflecting a "deficit" state; if the curve shows frequent alternation between rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state. The slope of the curve depicts the rate of change of the cumulative anomaly; a positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus; a negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit. On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase; the maximum point represents the highest peak of historical cumulative surplus; conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase.

[0014] A further improvement of this invention is that, in the third data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily power generation of wind and solar are converted into a standard power generation index sequence. The standard power generation index is used to measure the abnormal level of new energy power and electricity data. While intuitively reflecting whether new energy is too much or too little, the standard power generation index eliminates the absolute value difference caused by regional differences or different statistical scales, so that various power generation anomalies can be compared across time and space under a unified scale. The conversion process of the standard power generation index includes: first, fitting the probability distribution of the historical power and electricity series to construct its cumulative distribution function, and then mapping the cumulative probability to the standard normal distribution to obtain the Z-score series with a mean of 0 and a standard deviation of 1, thereby achieving the standardization of the series.

[0015] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the new energy characteristic evaluation method based on anomaly analysis.

[0016] Compared with the prior art, the present invention has at least the following beneficial technical effects: This invention provides a powerful tool and a new perspective for evaluating the characteristics of new energy sources from the angle of anomaly analysis, and constructs a complete application process. Based on anomalies, cumulative anomalies, and standard power generation indices, it can reflect the characteristics of new energy sources from multiple perspectives. The anomaly analysis method proposed in this invention is applicable to analyzing the characteristics of new energy sources at different time and spatial scales, and is helpful for power system power balance and planning operation research. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the cumulative anomaly. Figure 2 A schematic diagram of the standard power generation index; Figure 3 A schematic diagram of the cumulative anomalies of daily utilization hours for wind power, photovoltaic power, and wind and solar power.

[0019] Figure 4 This is a structural block diagram of a new energy characteristic evaluation system based on anomaly analysis according to the present invention. Detailed Implementation

[0020] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0021] In the description of this invention, it should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0025] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0026] Example 1 This invention provides a method for evaluating the characteristics of new energy sources based on anomaly analysis, comprising: Step 1: Based on the characteristics of new energy wind and solar power generation that depend on meteorological factors such as wind speed and irradiance, establish the application process of anomaly analysis method in the evaluation of new energy characteristics.

[0027] Step 2: Introduce the anomaly.

[0028] The formula for defining the anomaly of new energy sources is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n This represents the total time period of the selected reference period. A positive anomaly indicates that the electricity and energy levels are above average at that time, while a negative anomaly indicates that they are below average.

[0029] Anomalies can be derived according to different dimensions. According to the time scale, they can be divided into intraday, intramonth, intrayear, and interannual anomalies; according to the spatial scale, they can be divided into single-unit, field group, regional, and system anomalies; according to the statistical method, they can be classified into anomaly probability distribution, maximum positive / negative anomaly, anomaly percentage, etc.

[0030] Step 3: Introduce cumulative anomalies.

[0031] Cumulative anomalies are time series obtained by successively summing anomaly sequences in chronological order. Cumulative anomalies effectively preserve the temporal information of renewable energy power and electricity, revealing the long-term trends in power and electricity consumption over time. They are defined as follows: (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time 0, which is 0 at time 0.

[0032] Cumulative anomaly diagram as shown Figure 1 As shown, when new energy data is above the average, the cumulative positive anomaly causes the curve to rise, reflecting a "surplus" state; when new energy data is below the average, the cumulative negative anomaly causes the curve to fall, reflecting a "deficit" state. If the curve shows frequent alternations of rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state.

[0033] The slope of the curve depicts the rate of change of the cumulative anomaly. A positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus. A negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit.

[0034] On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase. The maximum point represents the highest peak reached by historical cumulative surplus. Conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase. The minimum point reflects the lowest trough reached by historical cumulative deficit.

[0035] Step 4: Introduce the standard power generation index.

[0036] The Standard Generation Index is used to measure the level of anomalies in renewable energy power and electricity data. While intuitively reflecting whether renewable energy is excessive or insufficient, the Standard Generation Index eliminates the absolute value differences caused by regional differences or different statistical scales, enabling cross-temporal and spatial comparisons of various generation anomalies on a unified scale.

[0037] Figure 2 This demonstrates the conversion process of the standard power generation index. First, a probability distribution is fitted to the historical power and electricity data series to construct its cumulative distribution function. Then, this cumulative probability is mapped onto a standard normal distribution, resulting in a Z-score series with a mean of 0 and a standard deviation of 1, thus standardizing the series. This Z-score characterizes the degree of deviation of the current value from the historical series mean and statistical distribution.

[0038] The Standard Generation Index (SRI) achieves cross-temporal comparability of power and electricity output series across different regions and time scales by standardizing the data to unify the scale and eliminate dimensions, and provides a clear probabilistic meaning. Because it approximately follows a standard normal distribution, the extreme properties of the standard normal distribution can be directly used for risk assessment of abnormal generation events. Based on the statistical characteristics of the standard normal distribution (…),… Table 1 shows the SPGI level classification and corresponding quantile probabilities, establishing a unified risk measurement standard.

[0039] Table 1 Classification of Standard Power Generation Index Levels

[0040] The specific calculation process for the standard power generation index is as follows: 1) Data Preprocessing. Collect new energy power and power consumption data for the target area. Imput and correct missing or outlier values ​​to ensure the integrity and consistency of the sample.

[0041] 2) Kernel density estimation. By selecting a suitable kernel function and bandwidth parameters, kernel density estimation is performed on historical electricity and power data to construct a probability density function. .

[0042] 3) Construction of the cumulative distribution function. Using numerical integration methods, the probability density function is constructed... Integrating over the interval of the independent variable yields the cumulative distribution function. : (3) And normalize it to ensure .

[0043] 4) Mapping to the standard normal distribution. This involves mapping the cumulative distribution function... The quantiles mapped to the standard normal distribution are used as the standardization index, with their corresponding Z-values: (4) Its distribution approximately follows a normal distribution with a mean of 0 and a standard deviation of 1, quantifying the degree of deviation of the current value from the historical average level and distribution characteristics.

[0044] Step 5: Collect historical power output data of new energy sources in the target area, and apply anomaly analysis to evaluate the characteristics of new energy sources in the target area.

[0045] Example 2 We will take the new energy data of Northwest China as an example for further detailed explanation.

[0046] The data used are historical daily utilization hours of wind and solar power output in Northwest China from 2020 to 2023. Cumulative anomaly and the standard power generation index are selected to illustrate the practical application process of the anomaly analysis method.

[0047] The cumulative anomaly curve of daily power generation from new energy sources in Northwest China is shown below. Figure 3As shown, new energy sources exhibit distinct seasonal characteristics, with high generation rates in summer and low generation rates in winter. From January to mid-February 2020, the generation period was low, with wind power cumulative anomaly plummeting from 0h to -120h at a rate of -2.67h / day, marking the lowest point in four years; during the same period, solar power only dropped to -28h at a rate of -0.65h / day. Subsequently, wind and solar power recovered to the zero line at rates of 0.96h / day and 0.41h / day, respectively. The lowest point for wind and solar power was -74h, recovering at a rate of 0.71h / day, highlighting the complementary advantages of wind and solar power.

[0048] The peak production period was from March to August 2022, with wind power increasing from -108 hours to 87 hours at a rate of 1.06 hours per day; solar power increasing from -40 hours to 64 hours at a rate of 0.59 hours per day; and combined wind and solar power increasing from -60 hours to 88 hours at a rate of 0.83 hours per day. This period corresponds to a typical high-yield period with favorable wind conditions and ample sunshine.

[0049] SPGI at different durations can be used to comprehensively assess the low-risk of renewable energy generation. Table 2 shows... For continuous computation based on sliding window i SPGI corresponding to daily cumulative power generation; statistics for each season. The number of windows less than -1.

[0050] From a seasonal perspective, the probability of frequent minor solar flare events is significantly higher in winter than in other seasons. Taking a 7-day window as an example, wind power and solar power have 135 and 130 such events respectively in winter; while wind power has fewer than 8 and 7 such events respectively in spring and summer, and solar power has fewer than 17 and 4 such events respectively in spring and summer. This indicates that the period with the highest risk of minor solar flare events throughout the year is winter, characterized by persistent low wind speeds and frequent continuous irradiance.

[0051] The impact of duration on the frequency of occurrences is seasonally dependent. As the window increased from 1 day to 7 days, the number of low-yield occurrences in winter continued to rise, with wind power increasing from 112 to 135 times and photovoltaic power from 93 to 130 times, reflecting that insufficient power generation in winter is characterized by multi-day duration. In contrast, the number of low-yield occurrences in spring and summer decreased significantly, indicating that low-yield occurrences in spring and summer are mostly caused by short-term low wind speeds or short-term low radiation, are difficult to sustain, and have a more serious risk of sudden occurrence.

[0052] Furthermore, wind and solar power complement each other in spring and summer: the number of low-generation events is zero within the 7-day window, indicating that wind and solar power typically do not experience multiple days of low generation simultaneously. However, the number of low-generation events for wind and solar power increases in winter, indicating that persistently low wind speeds and persistently low irradiance coexist in winter, weakening the complementary effect and increasing the overall risk of low generation in the system.

[0053] Table 2. Number of times new energy production was low in Northwest China at different time scales

[0054] Example 3 like Figure 4 As shown, the present invention provides a new energy characteristic evaluation system based on anomaly analysis, comprising: The data collection and preprocessing unit collects historical data on actual output of new energy wind and solar power and actual daily power generation of wind and solar power, and preprocesses the data. The first data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into anomaly sequences. The second data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a cumulative anomaly sequence. The third data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a standard power generation index sequence. The evaluation unit, based on the anomaly sequence, cumulative anomaly sequence, and standard power generation index sequence, applies anomaly analysis to evaluate the new energy characteristics of the target area and obtains the new energy characteristic evaluation results.

[0055] In the first data conversion unit of this embodiment, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into an anomaly sequence, wherein the definition formula for new energy anomaly is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n The total time for the selected reference period; a positive anomaly indicates that the power and electricity consumption at that time are above the average level, while a negative anomaly indicates that they are below the average level; Anomalies are derived according to different dimensions: according to time scale, they are divided into intraday, intramonth, intrayear, and interannual anomalies; according to spatial scale, they are divided into single-machine, field cluster, regional, and system anomalies; and according to statistical methods, they are divided into anomaly probability distribution, maximum positive / negative anomaly, and anomaly percentage.

[0056] In the second data conversion unit of this embodiment, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into a cumulative anomaly sequence. The cumulative anomaly is a time series obtained by successively accumulating the anomaly sequence in chronological order, defined as... (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time of day, which is 0 at 0:00; When new energy data is higher than the average, the positive anomaly accumulates and causes the curve to rise, reflecting a "surplus" state; when new energy data is lower than the average, the negative anomaly accumulates and causes the curve to fall, reflecting a "deficit" state; if the curve shows frequent alternation between rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state. The slope of the curve depicts the rate of change of the cumulative anomaly; a positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus; a negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit. On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase; the maximum point represents the highest peak of historical cumulative surplus; conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase.

[0057] In the third data conversion unit of this embodiment, the preprocessed historical actual values ​​of wind and solar power output and actual daily power generation of wind and solar are converted into a standard power generation index sequence. The standard power generation index is used to measure the abnormal level of new energy power and electricity data. While intuitively reflecting whether new energy is too much or too little, the standard power generation index eliminates the absolute value difference caused by regional differences or different statistical scales, so that various power generation anomalies can be compared across time and space under a unified scale. The conversion process of the standard power generation index includes: first, fitting the probability distribution of the historical power and electricity series to construct its cumulative distribution function, and then mapping the cumulative probability to the standard normal distribution to obtain the Z-score series with a mean of 0 and a standard deviation of 1, thereby achieving the standardization of the series.

[0058] Example 4 The present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a new energy characteristic evaluation method based on anomaly analysis.

[0059] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This application is described with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0064] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A method for evaluating the characteristics of new energy sources based on anomaly analysis, characterized in that, include: Step 1: Collect historical data on actual output of wind and solar power and actual daily power generation of wind and solar energy, and preprocess the data; Step 2: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into anomaly sequences; Step 3: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a cumulative anomaly sequence; Step 4: Convert the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a standard power generation index sequence; Step 5: Based on the anomaly sequence, cumulative anomaly sequence, and standard power generation index sequence, apply the anomaly analysis method to evaluate the new energy characteristics of the target area and obtain the new energy characteristic evaluation results.

2. The new energy characteristic evaluation method based on anomaly analysis according to claim 1, characterized in that, In step two, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into anomaly sequences. The definition formula for renewable energy anomalies is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n The total time for the selected reference period; a positive anomaly indicates that the power and electricity consumption at that time are above the average level, while a negative anomaly indicates that they are below the average level; Anomalies are derived according to different dimensions: according to time scale, they are divided into intraday, intramonth, intrayear, and interannual anomalies; according to spatial scale, they are divided into single-machine, field cluster, regional, and system anomalies; and according to statistical methods, they are divided into anomaly probability distribution, maximum positive / negative anomaly, and anomaly percentage.

3. The new energy characteristic evaluation method based on anomaly analysis according to claim 1, characterized in that, In step three, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are transformed into a cumulative anomaly sequence. The cumulative anomaly is a time series obtained by successively accumulating the anomaly sequences in chronological order, defined as follows: (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time of day, which is 0 at 0:00; When new energy data is higher than the average, the positive anomaly accumulates and the curve rises, reflecting a "surplus" state; when new energy data is lower than the average, the negative anomaly accumulates and the curve falls, reflecting a "deficit" state; if the curve shows frequent alternation between rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state. The slope of the curve depicts the rate of change of the cumulative anomaly; a positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus; a negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit. On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase; the maximum point represents the highest peak of historical cumulative surplus; conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase.

4. The new energy characteristic evaluation method based on anomaly analysis according to claim 1, characterized in that, In step four, the preprocessed historical actual values ​​of wind and solar power output and actual daily power generation of wind and solar are transformed into a standard power generation index sequence. The standard power generation index is used to measure the abnormal level of new energy power and electricity data. While intuitively reflecting whether new energy is too much or too little, the standard power generation index eliminates the absolute value difference caused by regional differences or different statistical scales, so that various power generation anomalies can be compared across time and space under a unified scale. The conversion process of the standard power generation index includes: first, fitting the probability distribution of the historical power and electricity series to construct its cumulative distribution function, and then mapping the cumulative probability to the standard normal distribution to obtain the Z-score series with a mean of 0 and a standard deviation of 1, thereby achieving the standardization of the series.

5. The new energy characteristic evaluation method based on anomaly analysis according to claim 4, characterized in that, The specific calculation process for the standard power generation index is as follows: Data preprocessing: Collect new energy power and power data for the target area; imput and correct missing or outlier values ​​to ensure the integrity and consistency of the sample; Kernel density estimation: By selecting a suitable kernel function and bandwidth parameters, kernel density estimation is performed on historical power and electricity data to construct a probability density function. ; Construction of the cumulative distribution function: Using numerical integration methods, the probability density function is... Integrating over the interval of the independent variable yields the cumulative distribution function. : (3) And normalize it to ensure ; Standard normal distribution mapping: mapping the cumulative distribution function The quantiles mapped to the standard normal distribution are used as the standardization index, with their corresponding Z-values: (4) Its distribution approximately follows a normal distribution with a mean of 0 and a standard deviation of 1, quantifying the degree of deviation of the current value from the historical average level and distribution characteristics.

6. A new energy characteristic evaluation system based on anomaly analysis, characterized in that, include: The data collection and preprocessing unit collects historical data on actual output of new energy wind and solar power and actual daily power generation of wind and solar power, and preprocesses the data. The first data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into anomaly sequences. The second data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a cumulative anomaly sequence. The third data conversion unit converts the pre-processed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation into a standard power generation index sequence. The evaluation unit, based on the anomaly sequence, cumulative anomaly sequence, and standard power generation index sequence, applies anomaly analysis to evaluate the new energy characteristics of the target area and obtains the new energy characteristic evaluation results.

7. The new energy characteristic evaluation system based on anomaly analysis according to claim 6, characterized in that, In the first data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into an anomaly sequence. The definition formula for the anomaly of new energy sources is as follows: (1) In the formula: For new energy t The time-related power and energy anomalies; For new energy t The actual power and electricity consumption at that time; n The total time for the selected reference period; a positive anomaly indicates that the power and electricity consumption at that time are above the average level, while a negative anomaly indicates that they are below the average level; Anomalies are derived according to different dimensions: according to time scale, they are divided into intraday, intramonth, intrayear, and interannual anomalies; according to spatial scale, they are divided into single-machine, field cluster, regional, and system anomalies; and according to statistical methods, they are divided into anomaly probability distribution, maximum positive / negative anomaly, and anomaly percentage.

8. The new energy characteristic evaluation system based on anomaly analysis according to claim 6, characterized in that, In the second data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily wind and solar power generation are converted into a cumulative anomaly sequence. The cumulative anomaly is a time series obtained by successively accumulating the anomaly sequences in chronological order, defined as follows: (2) In the formula: for t The cumulative anomaly of electricity and energy consumption at time of day, which is 0 at 0:00; When new energy data is higher than the average, the positive anomaly accumulates and the curve rises, reflecting a "surplus" state; when new energy data is lower than the average, the negative anomaly accumulates and the curve falls, reflecting a "deficit" state; if the curve shows frequent alternation between rising and falling in the short term, it indicates that new energy is fluctuating significantly around the average in the short term; if it shows a long-term rise or fall, it indicates that new energy is in a long-term surplus or deficit state. The slope of the curve depicts the rate of change of the cumulative anomaly; a positive slope corresponds to an upward curve, indicating that electricity and power consumption are consistently higher than the average, and the larger the slope, the more significant the trend of accumulated surplus; a negative slope corresponds to a downward curve, indicating that electricity and power consumption are consistently lower than the average, and the smaller the slope, the more severe the trend of accumulated deficit. On the cumulative anomaly curve, the maximum point marks the end of a long-term surplus phase and the beginning of a deficit phase; the maximum point represents the highest peak of historical cumulative surplus; conversely, the minimum point indicates the end of a long-term deficit phase and the beginning of a surplus phase.

9. The new energy characteristic evaluation method based on anomaly analysis according to claim 6, characterized in that, In the third data conversion unit, the preprocessed historical actual values ​​of wind and solar power output and actual daily power generation of wind and solar are converted into a standard power generation index sequence. The standard power generation index is used to measure the abnormal level of new energy power and electricity data. While intuitively reflecting whether new energy is too much or too little, the standard power generation index eliminates the absolute value difference caused by regional differences or different statistical scales, so that various power generation anomalies can be compared across time and space under a unified scale. The conversion process of the standard power generation index includes: first, fitting the probability distribution of the historical power and electricity series to construct its cumulative distribution function, and then mapping the cumulative probability to the standard normal distribution to obtain the Z-score series with a mean of 0 and a standard deviation of 1, thereby achieving the standardization of the series.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the new energy characteristic evaluation method based on anomaly analysis according to any one of claims 1-5.

Images