Micro-grid intelligent regulation and control method for digital power grid

Abstract

The invention relates to the technical field of data processing, in particular to a micro-grid intelligent regulation and control method for a digital power grid. The method comprises the following steps: acquiring reversibility characterization values corresponding to all first parameter sequence pairs in a first parameter sequence pair set; obtaining a second parameter sequence pair set according to the reversion representation value corresponding to the first parameter sequence pair; obtaining a complementarity characterization value corresponding to the second parameter sequence pair according to the first curve corresponding to the parameter sequences forming the second parameter sequence pair; obtaining a to-be-fused parameter sequence set and a non-fused parameter sequence according to the complementarity characterization value; the method comprises the steps of collecting a to-be-fused parameter sequence set, fusing sequences in the to-be-fused parameter sequence set, recording the fused sequence as a fused parameter sequence corresponding to the to-be-fused parameter sequence set, constructing a scheduling model according to the fused parameter sequence and a non-fused parameter sequence, and performing intelligent regulation and control on a microgrid according to the constructed scheduling model. According to the invention, the reliability and accuracy of intelligent regulation and control of the micro-grid can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a microgrid intelligent control method for a digital power grid. Background Art

[0002] Microgrid is an important part of digital power grid. By integrating distributed power sources, energy storage devices and intelligent control technologies, it can not only realize self-control, self-protection and self-management of power system, but also improve the overall efficiency, stability, reliability and safety of power grid. That is, microgrid is closely related to the efficiency, stability, reliability and safety of power grid. At present, the efficiency, stability, reliability and safety of power grid are usually ensured by intelligent regulation of microgrid in digital power grid. That is, accurate and reliable intelligent regulation of microgrid in digital power grid is crucial to ensure the efficiency, stability, reliability and safety of power grid.

[0003] In the prior art, generally, various electrical parameters in the microgrid are first collected in time series, and then the various types of collected time series data are independently monitored and analyzed. After that, a scheduling model is constructed based on the independent analysis results of each type of time series data. Finally, the intelligent regulation of the microgrid is realized based on the scheduling model. However, this method of independently monitoring and analyzing various types of time series data will cause the constructed scheduling model to be unreliable or have low accuracy. When the constructed scheduling model is unreliable or has low accuracy, it will lead to the subsequent inability to reliably and accurately perform intelligent regulation of the microgrid, thereby failing to guarantee the efficiency, stability, reliability and safety of the power grid. Therefore, it is an urgent problem to build a reliable scheduling model to improve the reliability and accuracy of intelligent regulation of the microgrid. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a microgrid intelligent control method for a digital power grid, and the technical solution adopted is as follows: An embodiment of the present invention provides a microgrid intelligent control method for a digital power grid, comprising the following steps: Obtain a set of parameter sequences to be analyzed corresponding to nodes in the microgrid and a first curve and a second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed, wherein the set of parameter sequences consists of A parameter sequences, where A is greater than 1; According to the set of parameter sequences to be analyzed, the first curve and the second curve corresponding to the parameter sequences, obtaining a set of first parameter sequence pairs and oppositeness characterization values ​​corresponding to each first parameter sequence pair in the first parameter sequence pair set; Obtaining a second parameter sequence pair set according to the opposite characterization values ​​corresponding to the first parameter sequence pairs; Obtaining, according to a first curve corresponding to a parameter sequence constituting a second parameter sequence pair, a complementarity characterization value corresponding to the second parameter sequence pair, wherein the second parameter sequence pair belongs to the second parameter sequence pair set; According to the complementary characterization value, a set of parameter sequences to be fused and a non-fused parameter sequence are obtained; The sequences in the set of parameter sequences to be fused are fused, and the fused sequences are recorded as fused parameter sequences corresponding to the set of parameter sequences to be fused, a scheduling model is constructed according to the fused parameter sequence and the non-fused parameter sequence, and the constructed scheduling model performs intelligent regulation on the microgrid.

[0005] Beneficial effects: The present invention first obtains a set of parameter sequences to be analyzed corresponding to nodes in a microgrid and a first curve and a second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed; then, according to the set of parameter sequences to be analyzed and the first curve and the second curve corresponding to the parameter sequences, obtains a set of first parameter sequence pairs and the opposite characterization values ​​corresponding to each first parameter sequence pair in the set of first parameter sequence pairs; then, according to the opposite characterization values ​​corresponding to the first parameter sequence pairs, obtains a set of second parameter sequence pairs; and according to the first curve corresponding to the parameter sequences constituting the second parameter sequence pairs, obtains a complementary characterization value corresponding to the second parameter sequence pairs; then, according to the complementary characterization values, obtains a set of parameter sequences to be fused and a non-fused parameter sequence; finally, fuses the sequences in the set of parameter sequences to be fused, and records the fused sequence as a fused parameter sequence corresponding to the set of parameter sequences to be fused, and then constructs a scheduling model according to the fused parameter sequence and the non-fused parameter sequence, and performs intelligent regulation of the microgrid according to the constructed scheduling model. The scheduling model constructed by the present invention based on the fused parameter sequence and the non-fused parameter sequence is relatively reliable and has high precision, and the reliability and accuracy of the intelligent regulation of the microgrid can be improved according to the relatively reliable and high precision scheduling model. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0007] Figure 1 The present invention is a flow chart of a microgrid intelligent control method for a digital power grid. DETAILED DESCRIPTION

[0008] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the embodiments of the present invention.

[0009] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0010] This embodiment provides a microgrid intelligent control method for a digital power grid, which is described in detail as follows: like Figure 1 As shown, the microgrid intelligent control method for a digital power grid includes the following steps: Step S001: obtaining a set of parameter sequences to be analyzed corresponding to nodes in a microgrid and a first curve and a second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed.

[0011] At present, the dispatching model is generally constructed based on the independent analysis results of various types of time series data, and then the intelligent regulation of the microgrid is realized based on the constructed dispatching model. Since only the independent analysis of various types of time series data cannot fully reflect the overall operation status of the power grid or equipment, the dispatching model constructed based on the independent analysis results of various types of time series data will also have the problem of unreliability or low precision. When the dispatching model constructed is unreliable or has low precision, it will lead to the subsequent inability to reliably and accurately perform intelligent regulation of the microgrid, and thus the efficiency, stability, reliability and safety of the power grid cannot be guaranteed. In order to ensure the efficiency, stability, reliability and safety of the power grid, this embodiment subsequently determines the set of parameter sequences to be fused through the opposite characteristics and complementary characteristics between the parameter sequences, and fuses the set of parameter sequences to be fused, and then constructs the dispatching model through the fused sequence and the parameter sequence that does not need to be fused, and the dispatching model constructed according to this method is better, that is, the reliability and accuracy of the dispatching model are better, then based on the better dispatching model, the purpose of reliably and accurately performing intelligent regulation of the microgrid can be achieved, and the efficiency, stability, reliability and safety of the power grid can also be guaranteed.

[0012] In order to obtain a better scheduling model, this embodiment first needs to obtain a set of parameter sequences to be analyzed corresponding to the nodes in the microgrid, and for ease of understanding, this embodiment takes any node Q in the microgrid as an example for analysis, that is, the parameter sequences to be analyzed subsequently obtained are all parameter sequences corresponding to the same node Q, and the node in the microgrid refers to the basic component unit in the microgrid, including distributed power sources, energy storage devices, energy conversion devices, loads, monitoring and protection devices, etc., then in this embodiment, the set of parameter sequences to be analyzed corresponding to the node Q and the specific acquisition process of the first curve and the second curve corresponding to each parameter sequence to be analyzed in the set of parameter sequences to be analyzed are: At each monitoring moment in the monitoring time period corresponding to the current monitoring moment, A types of electrical parameters at the node Q position are obtained, and the time series sequences constructed by the same type of electrical parameters are all recorded as initial sequences corresponding to the node, and then all initial sequences are preprocessed, and the preprocessed sequences are recorded as parameter sequences to be analyzed corresponding to the node, and then the set constructed by all the obtained parameter sequences to be analyzed corresponding to the node Q is recorded as the parameter sequence set to be analyzed corresponding to the node Q, and the number of sequences in the parameter sequence set to be analyzed corresponding to the node Q is also A; in addition, the electrical parameters are collected by sensors and monitoring equipment installed at the node position, and the collected data is transmitted to the data center or cloud platform through a high-speed communication network.

[0013] In specific applications, the implementer needs to set the monitoring time period corresponding to the current monitoring moment, the time interval between adjacent monitoring moments, and the value of A according to actual conditions. For example, in this embodiment, the ten minutes before the current monitoring moment can be used as the monitoring time period corresponding to the current monitoring moment, and the monitoring time period corresponding to the current monitoring moment includes the current monitoring moment. In this embodiment, the time interval between adjacent monitoring moments can be set to 1 second. In this embodiment, the value of A can be set to 5, and the five types of electrical parameters to be collected are voltage, current, power, frequency and phase.

[0014] In addition, in this embodiment, the process of preprocessing the initial sequence at least includes processing of missing values ​​and processing of abnormal values.

[0015] After obtaining the set of parameter sequences to be analyzed, the first curve and the second curve corresponding to each parameter sequence to be analyzed in the set of parameter sequences to be analyzed are then obtained, and the specific acquisition process is: First, a mapping space is constructed, and the horizontal axis of the two-dimensional mapping space is time, and the vertical axis is the value of the parameter in the parameter sequence to be analyzed after data standardization.

[0016] For ease of understanding, this embodiment will take the acquisition process of the first curve and the second curve corresponding to any parameter sequence B in the set of parameter sequences to be analyzed as an example for description, specifically: firstly, data standardization or normalization is performed on all parameters in the parameter sequence B, and the sequence composed of the parameters after data standardization is recorded as the parameter sequence to be mapped corresponding to the parameter sequence B, and the parameters in the parameter sequence to be mapped are recorded as the parameters to be mapped; then, all the parameters to be mapped in the sequence to be mapped corresponding to the parameter sequence B are mapped to the two-dimensional mapping space, and the data points corresponding to the parameters to be mapped in the parameter sequence to be mapped can be obtained through mapping; then, the parameters in the parameter sequence to be mapped are mapped in the two-dimensional mapping space in the order of the horizontal coordinate value from small to large. The data points corresponding to the parameters to be mapped are connected, and the connected curve is recorded as the first curve corresponding to the parameter sequence B, and the ordinate of the data point corresponding to the parameter to be mapped in the sequence to be mapped corresponding to the parameter sequence B is the value of the corresponding parameter to be mapped, and the abscissa is the acquisition time. If a parameter to be mapped is obtained after the parameter p0 is standardized, then the abscissa value of the data point corresponding to the parameter to be mapped after mapping is the acquisition time of the parameter p0; then the first curve corresponding to the parameter sequence B is horizontally flipped, and the curve obtained after the horizontal flipping is recorded as the second curve corresponding to the parameter sequence B, and the detailed process of the horizontal flipping is a well-known technology, so it will not be described in detail in this embodiment.

[0017] Therefore, this embodiment can obtain the first curve and the second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed through the above process.

[0018] Step S002: obtaining a first parameter sequence pair set and oppositeness characterization values ​​corresponding to each first parameter sequence pair in the first parameter sequence pair set according to the parameter sequence set to be analyzed, the first curve and the second curve corresponding to the parameter sequence.

[0019] In order to make the scheduling model constructed later better, this embodiment needs to first analyze the opposite characteristics between parameter sequences, which can reflect the complementary characteristics between electrical parameter sequences. This embodiment mainly merges the sequences with more obvious complementary characteristics. Therefore, this embodiment needs to obtain the opposite characterization values ​​corresponding to the first parameter sequence pair set and each first parameter sequence pair in the first parameter sequence pair set according to the parameter sequence set to be analyzed and the first curve and the second curve corresponding to the parameter sequence. The specific acquisition process is as follows: First, the parameter sequences in the parameter sequence set to be analyzed are combined in pairs without duplication, and the set constructed by all electrical parameter sequence pairs obtained after the combination is recorded as the first parameter sequence pair set, and the sequence pairs in the first parameter sequence pair set are all recorded as first parameter sequence pairs. Next, the opposite characterization value corresponding to the first parameter sequence pair is obtained, and for ease of understanding, the acquisition process of the opposite characterization value corresponding to any first parameter sequence pair C in the first parameter sequence pair set will be described as an example, specifically: First, the first parameter sequence in the first parameter sequence pair C is recorded as sequence C1, and the second parameter sequence in the first parameter sequence pair C is recorded as sequence C2, and for all first parameter sequence pairs, in the parameter sequence set to be analyzed, the first parameter sequence in all first parameter sequence pairs is located in front of the second parameter sequence in the corresponding first parameter sequence pair; then, the total number of peak points on the first curve corresponding to sequence C1 is obtained, and recorded as the first quantity characterization value; then, the total number of peak points on the second curve corresponding to sequence C2 is obtained, and recorded as the second quantity characterization value; then, the total number of intersections between the first curve corresponding to sequence C1 and the first curve corresponding to sequence C2 is obtained, and recorded as the third quantity characterization value; and then, the first characterization value is obtained according to the first quantity characterization value, the second quantity characterization value and the third quantity characterization value.

[0020] In this embodiment, the specific method for obtaining the first characterization value is: first, the absolute value of the difference between the first quantity characterization value and the second quantity characterization value is obtained and recorded as the first difference, and then the value obtained after negative correlation mapping of the first difference is recorded as the first mapping value, and then the mean of the first quantity characterization value and the second quantity characterization value is obtained and recorded as the first mean; then the ratio of the third quantity characterization value to the first mean is calculated and recorded as the first ratio, and the value obtained after negative correlation mapping of the first ratio is recorded as the second mapping value; finally, the first mapping value and the second mapping value are weightedly fused, and the result of the weighted fusion is used as the first characterization value; and in this embodiment, the specific expression for obtaining the first characterization value is:

[0021] in, is the first characterization value, is the first weight value, is the second weight value, exp() is an exponential function with a constant e as the base, F1 is the first quantity characterization value, F2 is the second quantity characterization value, F3 is the third quantity characterization value, is the first mean. And when and The smaller the value of The larger the value of The larger the value of , the more opposite the first curve corresponding to sequence C1 and the first curve corresponding to sequence C2 are, and the stronger the opposite feature is, the stronger the complementary feature between the two sequences may be. The stronger complementary feature means that the first curve corresponding to one sequence is rising, while the first curve corresponding to the other sequence is falling. and The larger the value of The smaller the value of The smaller the value of , the less the first curve corresponding to the sequence C1 and the first curve corresponding to the sequence C2 have the opposite characteristic.

[0022] Next, the slope value of the straight line formed by the first data point and the last data point on the first curve corresponding to the sequence C1 is obtained and recorded as the first slope value; then the slope value of the straight line formed by the first data point and the last data point on the second curve corresponding to the sequence C2 is obtained and recorded as the second slope value. Then, the ratio of the first slope value to the second slope value is obtained, and the value obtained by rounding up the ratio of the first slope value to the second slope value is recorded as the second ratio; then the hyperbolic tangent value of the second ratio is obtained and recorded as the first tangent value, and then the difference between the preset first constant and the first tangent value is used as the second characterization value; and in this embodiment, the specific expression for obtaining the second characterization value is:

[0023] in, is the second characterization value, tanh() is the hyperbolic tangent function, K1 is the first slope value, K2 is the second slope value, C1 is the preset first constant, is the rounding symbol; and in specific applications, the implementer needs to set the value of C1 according to the actual situation, such as setting the value of C1 to 1 in this embodiment; in addition, when The larger the value of The larger the value of is, the closer it is to 1, and when The larger the value of The smaller the value of The smaller the value of is, the less opposite the first curve corresponding to sequence C1 is to the first curve corresponding to sequence C2. The smaller the value of The smaller the value of The smaller the value of The larger the value of The larger the value of , the more opposite the first curve corresponding to the sequence C1 and the first curve corresponding to the sequence C2 are.

[0024] After obtaining the first characterization value and the second characterization value, it is necessary to continue to obtain the average of the first characterization value and the second characterization value, and round up the average of the first characterization value and the second characterization value, and record the rounded value as the opposite characterization value corresponding to the first parameter sequence pair C, and the larger the opposite characterization value, the stronger the opposite characteristic between the first curve corresponding to sequence C1 and the first curve corresponding to sequence C2, and when the opposite characteristic between the first curve corresponding to sequence C1 and the first curve corresponding to sequence C2 is stronger, there is a greater possibility that one of the two electrical parameter sequences is in an ascending state and the other is in a descending state, and the larger the opposite characterization value, the greater the probability that there is a complementary feature between the first curve corresponding to sequence C1 and the first curve corresponding to sequence C2; ​​in addition, as another implementation method, in the process of calculating the opposite characterization value between sequence C1 and sequence C2, the opposite characterization value can also be determined by analyzing the second curve of sequence C1 and the first curve of sequence C2.

[0025] Therefore, this embodiment can obtain the first parameter sequence pair set and the opposite characterization value corresponding to each first parameter sequence pair in the first parameter sequence pair set through the above process.

[0026] Step S003, obtaining a second parameter sequence pair set according to the opposite characterization value corresponding to the first parameter sequence pair; obtaining a complementary characterization value corresponding to the second parameter sequence pair according to the first curve corresponding to the parameter sequence constituting the second parameter sequence pair, and the second parameter sequence pair belongs to the second parameter sequence pair set.

[0027] After obtaining the opposite characterization value corresponding to the first parameter sequence pair, this embodiment then obtains a second parameter sequence pair set according to the opposite characterization value corresponding to the initial electrical parameter sequence pair, and the second parameter sequence pair set is the basis for subsequently obtaining the parameter sequence set to be fused and the non-fused parameter sequence, so the process of obtaining the second parameter sequence pair set is: For any first parameter sequence pair C, if the opposite characterization value corresponding to the first parameter sequence pair C is not less than the preset first threshold, it is determined that the opposite characteristics between the first curves corresponding to the two sequences in the first parameter sequence pair C are stronger, then the first parameter sequence pair C is recorded as the second parameter sequence pair, if the opposite characterization value corresponding to the first parameter sequence pair C is less than the preset first threshold, it is determined that the opposite characteristics between the first curves corresponding to the two sequences in the first parameter sequence pair C are weaker, then in order to reduce the amount of calculation, there is no need to further perform fusion analysis on these sequences. In specific applications, the implementer needs to set the preset first threshold according to actual conditions, such as setting the preset first threshold to 0.7 in this embodiment.

[0028] Therefore, according to the above process, all second parameter sequence pairs in the first parameter sequence pair set can be obtained, and then a set constructed by all second parameter sequence pairs in the first parameter sequence pair set is recorded as the second parameter sequence pair set.

[0029] Since the subsequent embodiment of this invention mainly fuses sequences with more obvious complementary characteristics, and the obvious complementary characteristics mean that different parameter sequences have differences in the change trends, but at the same time these differences can complement each other, and if these sequences with obvious complementary characteristics are fused, not only can their respective advantages be combined, but also the shortcomings of a single sequence can be made up, thereby providing more comprehensive information, although the above-mentioned opposite characterization value obtained can characterize the probability of complementarity between sequences, it cannot accurately characterize the strength of the complementary characteristics between sequences, so after obtaining the second parameter sequence pair set, this embodiment will obtain the complementary characterization value corresponding to the second parameter sequence pair according to the first curve corresponding to the parameter sequence constituting the second parameter sequence pair; in addition, for ease of understanding, this embodiment will take the acquisition process of the complementary characterization value corresponding to any second parameter sequence pair D in the second parameter sequence pair set as an example to describe, that is, the acquisition process of the complementary characterization value corresponding to the second parameter sequence pair D is: First, the two parameter sequences in the second parameter sequence pair D are respectively recorded as sequence D1 and sequence D2, and the straight line formed by the first data point and the last data point on the first curve corresponding to sequence D1 is obtained and recorded as the first straight line, and the straight line formed by the first data point and the last data point on the first curve corresponding to sequence D2 is obtained and recorded as the second straight line; then, the average of the slope of the first straight line and the slope of the second straight line is calculated, and recorded as the target slope; then, the average of the intercept of the first straight line and the intercept of the second straight line is obtained, and recorded as the target intercept; then, a straight line with a slope and an intercept equal to the target slope and the target intercept is constructed, and recorded as the center straight line corresponding to the second parameter sequence pair D.

[0030] Then, on the first curve corresponding to sequence D1 and the first curve corresponding to sequence D2, the data point pairs consisting of data points with the same horizontal coordinate value are recorded as feature data point pairs, that is, of the two data points in the feature data point pair, one belongs to the first curve corresponding to sequence D1, and the other belongs to the first curve corresponding to sequence D2. Thereafter, the set constructed by all the acquired feature data point pairs is recorded as the feature data point pair set corresponding to the second parameter sequence pair D, and the number of feature data point pairs in the feature data point pair set corresponding to the second parameter sequence pair D is the same as the number of data points on the first curve corresponding to sequence D1 or sequence D2.

[0031] After obtaining the central straight line and the set of characteristic data point pairs corresponding to the second parameter sequence pair D, the characteristic difference values ​​corresponding to each characteristic data point pair in the characteristic data point pair set are obtained based on the central straight line and the characteristic data point pairs in the characteristic data point pair set; then the mean of the characteristic difference values ​​corresponding to all the characteristic data point pairs in the characteristic data point pair set is obtained and recorded as the mean to be processed, and then the mean to be processed is normalized and the normalized value is recorded as the normalized mean; finally, the value obtained by subtracting the normalized mean from the preset first constant is used as the complementary characterization value corresponding to the second parameter sequence pair D.

[0032] In addition, in this embodiment, the process of obtaining the feature difference value corresponding to the feature data point pair in the feature data point pair set is as follows: for the cth feature data point pair in the feature data point pair set: First, the two data points in the c-th feature data point pair are recorded as the first data point and the second data point respectively; then, on the central straight line, the data point with the same horizontal coordinate value as the data point in the c-th feature data point pair is obtained, and recorded as the comparison data point corresponding to the c-th feature data point pair; then, the Euclidean distance between the first data point and the comparison data point is recorded as the first distance, the Euclidean distance between the second data point and the comparison data point is recorded as the second distance, and the absolute value of the difference between the first distance and the second distance is recorded as the feature difference corresponding to the c-th feature data point pair.

[0033] In this embodiment, the specific expression for obtaining the complementary characterization value corresponding to the second parameter sequence pair D is:

[0034] in, is the complementary characterization value corresponding to the second parameter sequence pair D, Norm() is the normalization function, is the total number of feature data point pairs in the feature data point pair set corresponding to the second parameter sequence pair D, is the feature difference corresponding to the cth feature data point pair, , is the Euclidean distance between the first data point in the c-th feature data point pair and the comparison data point corresponding to the c-th feature data point pair, is the Euclidean distance between the second data point in the c-th feature data point pair and the comparison data point corresponding to the c-th feature data point pair; and when The smaller the value of The larger the value of The larger the value of is, the stronger the complementary characteristics between the two parameter sequences constituting the second parameter sequence pair D are. The larger the value of The smaller the value of The smaller the value of , the weaker the complementary characteristics between the two parameter sequences constituting the second parameter sequence pair D.

[0035] Therefore, this embodiment can obtain the complementary characterization value corresponding to each second parameter sequence pair through the above process, and when the complementary characterization value corresponding to the second parameter sequence pair is larger, it indicates that the complementary characteristics between the two parameter sequences constituting the second parameter sequence pair are stronger; in addition, the complementary characterization value is also the basis for subsequently determining the sequence to be fused.

[0036] Step S004: obtaining a set of parameter sequences to be fused and a non-fused parameter sequence according to the complementary characterization value.

[0037] After obtaining the complementary characterization value corresponding to the second parameter sequence pair, this embodiment will then determine the set of parameter sequences to be fused and the non-fused parameter sequence by analyzing the complementary characterization value corresponding to the second parameter sequence pair, and the specific process is as follows: First, in the second parameter sequence pair set, the set constructed by all second parameter sequence pairs whose complementary characterization values ​​are not less than the preset second threshold is recorded as the comprehensive sequence pair set, and the set constructed by all parameter sequences appearing in the comprehensive sequence pair set is recorded as the parameter sequence set to be selected, and the total number of sequences in the parameter sequence set to be selected is N. For example, if there are 3 parameter sequence pairs in the comprehensive sequence pair set, namely sequence pairs T1, T2 and T3, and sequence pair T1 is composed of sequence t1 and sequence t2, sequence pair T2 is composed of sequence t2 and sequence t3, and sequence pair T3 is composed of sequence t1 and sequence t4, then all sequences appearing in the comprehensive sequence pair set include sequence t1, sequence t2, sequence t3 and sequence t4, that is, at this time, the parameter sequence set to be selected is composed of sequence t1, sequence t2, sequence t3 and sequence t4. In addition, in specific applications, the implementer needs to set the preset second threshold according to actual conditions, such as setting the preset second threshold to 0.8 in this embodiment.

[0038] After obtaining the set of parameter sequences to be selected, this embodiment will next specifically describe the process of obtaining the set of parameter sequences to be fused, which is specifically: First, in the set of parameter sequences to be selected, n parameter sequences are randomly selected for non-repeated permutations and combinations, and the set formed by all sequences in each permutation result obtained after the permutation is completed is recorded as the nth sequence feature set, and the number of the nth sequence feature sets is C(N,n), where , is a factorial symbol, and the value of n in this embodiment is 2; for example, if the value of n is 2, and the set of parameter sequences to be selected is composed of sequence t1, sequence t2, and sequence t3, then arbitrarily select n parameter sequences for non-repeating permutations and combinations, and the obtained nth sequence feature sets are 3, namely {t1, t2}, {t2, t3} and {t1, t3}; then continue to arbitrarily select n+1 parameter sequences from the set of parameter sequences to be selected for non-repeating permutations and combinations, and the set formed by all sequences in each permutation result obtained after the permutation is completed is recorded as the n+1th sequence feature set, and the number of the n+1th sequence feature sets is C(N, n+1), and so on, until the number of sequences in the obtained sequence feature set is N-1, stop, and count all the obtained sequence feature sets.

[0039] Therefore, multiple sequence feature sets can be obtained through the above process, and then all the obtained sequence feature sets are judged as the parameter sequence set to be fused, and this embodiment takes the judgment process of any sequence feature set as an example to describe, such as this embodiment takes the judgment process of the nth sequence feature set U as an example to describe, specifically: First, all the to-be-judged sequence sets corresponding to the n-th sequence feature set U, the feature sequence pair sets corresponding to the n-th sequence feature set U, and the feature sequence pair sets corresponding to the to-be-judged sequence sets are obtained.

[0040] Then, it is determined whether the feature sequence pair set corresponding to the n-th sequence feature set U belongs to the comprehensive sequence pair set. If so, it is further determined whether the feature sequence pair sets corresponding to all the sequence sets to be determined corresponding to the n-th sequence feature set U do not all belong to the comprehensive sequence pair set. If so, the n-th sequence feature set U is used as a parameter sequence set to be fused, that is, when it is determined that the feature sequence pair set corresponding to the n-th sequence feature set U belongs to the comprehensive sequence pair set and the feature sequence pair sets corresponding to all the sequence sets to be determined corresponding to the n-th sequence feature set U do not all belong to the comprehensive sequence pair set, then the n-th sequence feature set U is used as a parameter sequence set to be fused; and the feature sequence pair set belongs to the comprehensive sequence pair set means that all sequence pairs in the corresponding feature sequence pair set belong to the comprehensive sequence pair set, and the feature sequence pair set does not belong to the comprehensive sequence pair set means that the sequence pairs in the corresponding feature sequence pair set do not all belong to the comprehensive sequence pair set.

[0041] In this embodiment, the method for obtaining all the to-be-judged sequence sets corresponding to the n-th sequence feature set U is as follows: a set constructed by all parameter sequences in the second parameter sequence set except the n-th sequence feature set U is recorded as the remaining sequence set corresponding to the n-th sequence feature set U; then, based on the remaining sequence set, all the to-be-judged sequence sets corresponding to the n-th sequence feature set U are obtained, and the i-th to-be-judged sequence set corresponding to the n-th sequence feature set U is a new set formed by combining the i-th sequence in the remaining sequence set and the n-th sequence feature set U, that is, the number of to-be-judged sequence sets corresponding to the n-th sequence feature set U is the same as the number of sequences in the remaining sequence set.

[0042] In this embodiment, a method for obtaining a feature sequence pair set corresponding to a sequence feature set and a feature sequence pair set corresponding to the sequence set to be judged is as follows: performing non-repetitive pairwise combinations on all parameter sequences in the sequence feature set, and recording a set constructed by all sequence pairs obtained by the combinations as feature sequence pairs corresponding to the corresponding sequence feature set; performing non-repetitive pairwise combinations on all sequences in the sequence set to be judged, and recording a set constructed by all sequence pairs obtained by the combinations as feature sequence pairs corresponding to the sequence set to be judged.

[0043] Therefore, through the above process, the parameter sequence set to be fused can be obtained from all sequence feature sets; in addition, when the value of N is small, the parameter sequence set to be selected may be the parameter sequence set to be fused, so it is also necessary to judge whether the parameter sequence set to be selected belongs to the parameter sequence set to be fused. The specific judgment process is: obtain the feature sequence pair set corresponding to the parameter sequence set to be selected, if the feature sequence pair set corresponding to the parameter sequence set to be selected belongs to the comprehensive sequence pair set, then the parameter sequence set to be selected is judged to be the parameter sequence set to be fused.

[0044] After all the electrical parameter sequence sets to be fused are obtained, the non-fused parameter sequences can be obtained. The specific acquisition process is: in the parameter sequence set to be analyzed, all parameter sequences that do not belong to the parameter sequence set to be fused are recorded as non-fused parameter sequences.

[0045] Therefore, this embodiment can obtain all the parameter sequence sets to be fused and the non-fused parameter sequences through the above process.

[0046] Step S005, fusing the sequences in the set of parameter sequences to be fused, and recording the fused sequences as fused parameter sequences corresponding to the set of parameter sequences to be fused, constructing a scheduling model according to the fused parameter sequences and the non-fused parameter sequences, and performing intelligent control on the microgrid according to the constructed scheduling model.

[0047] Next, this embodiment will fuse each of the above-obtained parameter sequence sets to be fused, and record the fused sequence as the fused parameter sequence corresponding to the corresponding parameter sequence set to be fused; and the above process of this embodiment is analyzed for one node, that is, all the fused parameter sequences and non-fused parameter sequences obtained above are corresponding to the same node, and when constructing the scheduling model, it is necessary to refer to all the nodes in the microgrid, that is, this embodiment needs to obtain all the fused parameter sequences and all the non-fused parameter sequences corresponding to all the nodes in the microgrid according to the above process, and then construct a scheduling model according to all the fused parameter sequences and all the non-fused parameter sequences corresponding to all the nodes obtained, and then perform intelligent regulation of the microgrid according to the obtained scheduling model; and intelligent regulation of the microgrid can enable the grid to quickly switch to an independent operation mode when a fault occurs, and continuously supply power to critical loads, thereby effectively reducing the time and scope of power outages, while also improving the utilization of clean energy, enhancing the flexibility and safety of the grid, and optimizing resource allocation and economic benefits.

[0048] In specific applications, the implementer needs to select the fusion algorithm for fusing the sequences in the fusion parameter sequence set according to the actual situation. For example, in this embodiment, the weighted average method, weighted summation method, maximum method, minimum method, etc. can be selected to realize the fusion of the sequence, and the specific fusion process is also a known technology, so it will not be described in detail. In addition, the process of constructing a scheduling model and intelligently regulating the microgrid based on the scheduling model is also a known technology, so this embodiment will not be described in detail.

[0049] In summary, the present embodiment first obtains the set of parameter sequences to be analyzed corresponding to the nodes in the microgrid and the first curve and the second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed; then, according to the set of parameter sequences to be analyzed and the first curve and the second curve corresponding to the parameter sequences, obtains the opposite characterization values ​​corresponding to the first parameter sequence pairs and each first parameter sequence pair in the set of first parameter sequence pairs; then, according to the opposite characterization values ​​corresponding to the first parameter sequence pairs, obtains the set of second parameter sequence pairs; and according to the first curve corresponding to the parameter sequences constituting the second parameter sequence pairs, obtains the complementary characterization values ​​corresponding to the second parameter sequence pairs; then, according to the complementary characterization values, obtains the set of parameter sequences to be fused and the non-fused parameter sequences; finally, the sequences in the set of parameter sequences to be fused are fused, and the fused sequences are recorded as the fused parameter sequences corresponding to the set of parameter sequences to be fused, and then, according to the fused parameter sequences and the non-fused parameter sequences, a scheduling model is constructed, and the microgrid is intelligently controlled according to the constructed scheduling model. The scheduling model constructed according to the fused parameter sequences and the non-fused parameter sequences in the present embodiment is relatively reliable and has high precision, and the reliability and accuracy of the intelligent control of the microgrid can be improved according to the relatively reliable and high precision scheduling model.

[0050] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A microgrid intelligent control method for a digital power grid, characterized in that: The method comprises the following steps: Obtain a set of parameter sequences to be analyzed corresponding to nodes in the microgrid and a first curve and a second curve corresponding to each parameter sequence in the set of parameter sequences to be analyzed, wherein the set of parameter sequences consists of A parameter sequences, where A is greater than 1; According to the set of parameter sequences to be analyzed, the first curve and the second curve corresponding to the parameter sequences, obtaining a set of first parameter sequence pairs and oppositeness characterization values ​​corresponding to each first parameter sequence pair in the first parameter sequence pair set; Obtaining a second parameter sequence pair set according to the opposite characterization values ​​corresponding to the first parameter sequence pairs; Obtaining, according to a first curve corresponding to a parameter sequence constituting a second parameter sequence pair, a complementarity characterization value corresponding to the second parameter sequence pair, wherein the second parameter sequence pair belongs to the second parameter sequence pair set; According to the complementary characterization value, a set of parameter sequences to be fused and a non-fused parameter sequence are obtained; The sequences in the set of parameter sequences to be fused are fused, and the fused sequences are recorded as fused parameter sequences corresponding to the set of parameter sequences to be fused, a scheduling model is constructed according to the fused parameter sequence and the non-fused parameter sequence, and the microgrid is intelligently controlled according to the constructed scheduling model.

2. A microgrid intelligent control method for a digital power grid according to claim 1, characterized in that: The method for obtaining the first curve and the second curve corresponding to the parameter sequence includes: Construct a two-dimensional mapping space; For any parameter sequence B in the set of parameter sequences to be analyzed: data standardization is performed on all parameters in the parameter sequence B, and the sequence composed of parameters after data standardization is recorded as the parameter sequence to be mapped corresponding to the parameter sequence B, and the parameters in the parameter sequence to be mapped are the parameters to be mapped; all the parameters to be mapped in the sequence to be mapped are mapped to the two-dimensional mapping space to obtain data points corresponding to each parameter to be mapped in the parameter sequence to be mapped; the data points corresponding to the parameters to be mapped are connected in order from small to large in terms of the horizontal coordinate value, and the connected curve is recorded as the first curve corresponding to the parameter sequence B, and the vertical coordinates of the data points corresponding to the parameters to be mapped are the values ​​of the corresponding parameters to be mapped, and the horizontal coordinates are the acquisition time; the first curve corresponding to the parameter sequence B is horizontally flipped, and the curve after flipping is recorded as the second curve corresponding to the parameter sequence B.

3. A microgrid intelligent control method for a digital power grid according to claim 1, characterized in that: The method for obtaining the first parameter sequence pair set and the opposite characterization value corresponding to each first parameter sequence pair in the first parameter sequence pair set includes: Combining the parameter sequences in the parameter sequence set to be analyzed in pairs without duplication, and recording a set constructed by all parameter sequence pairs obtained after the combination as a first parameter sequence pair set, and recording all sequence pairs in the first parameter sequence pair set as first parameter sequence pairs; For any first parameter sequence pair C: record the two parameter sequences in the first parameter sequence pair C as sequence C1 and sequence C2 respectively, obtain the total number of peak points on the first curve corresponding to the sequence C1, and record it as the first quantity characterization value; obtain the total number of peak points on the second curve corresponding to the sequence C2, and record it as the second quantity characterization value; obtain the total number of intersections between the first curve corresponding to the sequence C1 and the first curve corresponding to the sequence C2, and record it as the third quantity characterization value; obtain the first characterization value according to the first quantity characterization value, the second quantity characterization value and the third quantity characterization value; the first characterization value corresponding to the sequence C1 The slope value of the straight line formed by the first data point and the last data point on a curve is recorded as the first slope value; the slope value of the straight line formed by the first data point and the last data point on the second curve corresponding to the sequence C2 is recorded as the second slope value; the integer value of the ratio of the first slope value to the second slope value is recorded as the second ratio, and the hyperbolic tangent value of the second ratio is recorded as the first tangent value, and the value obtained by subtracting the first tangent value from the preset first constant is used as the second characterization value; the integer value of the mean of the first characterization value and the second characterization value is used as the opposite characterization value corresponding to the first parameter sequence pair C.

4. A microgrid intelligent control method for a digital power grid as claimed in claim 3, characterized in that: The method for obtaining the first characterization value includes: The absolute value of the difference between the first quantity characterization value and the second quantity characterization value is recorded as the first difference; the value after negative correlation mapping of the first difference is recorded as the first mapping value; the mean of the first quantity characterization value and the second quantity characterization value is recorded as the first mean; the ratio of the third quantity characterization value to the first mean is recorded as the first ratio, and the value after negative correlation mapping of the first ratio is recorded as the second mapping value; the result of weighted fusion of the first mapping value and the second mapping value is used as the first characterization value.

5. A microgrid intelligent control method for a digital power grid according to claim 1, characterized in that: The method for obtaining the second parameter sequence pair set includes: In the first parameter sequence pair set, a set constructed of all first parameter sequence pairs whose opposite characterization values ​​are not less than a preset first threshold is recorded as a second parameter sequence pair set, and the parameter sequence pairs in the second parameter sequence pair set are recorded as second parameter sequence pairs.

6. A microgrid intelligent control method for a digital power grid according to claim 1, characterized in that: The method for obtaining the complementary characterization value corresponding to the second parameter sequence pair includes: For any second parameter sequence pair D in the second parameter sequence pair set: The two parameter sequences in the second parameter sequence pair D are respectively recorded as sequence D1 and sequence D2, the straight line formed by the first data point and the last data point on the first curve corresponding to the sequence D1 is recorded as the first straight line, and the straight line formed by the first data point and the last data point on the first curve corresponding to the sequence D2 is recorded as the second straight line; the average of the slope of the first straight line and the slope of the second straight line is recorded as the target slope; the average of the intercept of the first straight line and the intercept of the second straight line is recorded as the target intercept; a straight line with a slope and an intercept equal to the target slope and the target intercept is constructed, and recorded as the center straight line corresponding to the second parameter sequence pair D; On the first curve corresponding to the sequence D1 and the sequence D2, all data point pairs formed by data points with the same horizontal coordinate value are recorded as feature data point pairs, and the set constructed by all feature data point pairs is recorded as the feature data point pair set corresponding to the second parameter sequence pair D; according to the central straight line and the feature data point pairs, the feature difference corresponding to each feature data point pair in the feature data point pair set is obtained; The mean of the feature differences corresponding to all the feature data point pairs in the feature data point pair set is obtained, and recorded as the mean to be processed, the mean to be processed is normalized, and the normalized value is recorded as the normalized mean; the value obtained by subtracting the normalized mean from the preset first constant is used as the complementary characterization value corresponding to the second parameter sequence pair D.

7. A microgrid intelligent control method for a digital power grid according to claim 6, characterized in that: The method for obtaining the characteristic difference value corresponding to the characteristic data point pair includes: For the cth feature data point pair in the feature data point pair set: On the center straight line, obtain a data point with the same horizontal coordinate value as the data point in the c-th feature data point pair, and record it as the comparison data point corresponding to the c-th feature data point pair; record the two data points in the c-th feature data point pair as the first data point and the second data point, respectively, record the Euclidean distance between the first data point and the comparison data point as the first distance, record the Euclidean distance between the second data point and the comparison data point as the second distance, and record the absolute value of the difference between the first distance and the second distance as the feature difference corresponding to the c-th feature data point pair.

8. A microgrid intelligent control method for a digital power grid according to claim 1, characterized in that: The method for obtaining the set of parameter sequences to be fused and the non-fused parameter sequences includes: In the second parameter sequence pair set, a set constructed by all second parameter sequence pairs whose complementarity characterization values ​​are not less than a preset second threshold is recorded as a comprehensive sequence pair set, and a set constructed by all parameter sequences appearing in the comprehensive sequence pair set is recorded as a parameter sequence set to be selected, and the total number of sequences in the parameter sequence set to be selected is N; In the set of parameter sequences to be selected, n parameter sequences are randomly selected for non-repeating permutations and combinations, and the set formed by all parameter sequences in each permutation result obtained after the permutations are completed is recorded as the nth sequence feature set; n+1 parameter sequences are randomly selected from the set of parameter sequences to be selected for non-repeating permutations and combinations, and the set formed by all parameter sequences in each permutation result obtained after the permutations are completed is recorded as the n+1th sequence feature set, and so on, until the number of sequences in the obtained sequence feature set is N-1, and all the obtained sequence feature sets are statistically obtained, and n is less than N-1; Obtaining all to-be-judged sequence sets corresponding to each sequence feature set, feature sequence pair sets corresponding to the sequence feature set, and feature sequence pair sets corresponding to the to-be-judged sequence set; For any sequence feature set, if the feature sequence pair set corresponding to the sequence feature set belongs to the comprehensive sequence pair set, and the feature sequence pair sets corresponding to all the sequence sets to be judged corresponding to the sequence feature set do not belong to the comprehensive sequence pair set, then the sequence feature set is used as an electrical parameter sequence set to be fused; the feature sequence pair set belongs to the comprehensive sequence pair set means that all sequence pairs in the corresponding feature sequence pair set belong to the comprehensive sequence pair set, and the feature sequence pair set does not belong to the comprehensive sequence pair set means that none of the sequence pairs in the corresponding feature sequence pair set belong to the comprehensive sequence pair set; In the set of parameter sequences to be analyzed, all parameter sequences that do not belong to the set of parameter sequences to be fused are recorded as non-fused electrical parameter sequences.

9. A microgrid intelligent control method for a digital power grid according to claim 8, characterized in that: The method for acquiring all to-be-judged sequence sets corresponding to the sequence feature set includes: For any n-th sequence feature set U: the set constructed by all parameter sequences in the second parameter sequence set except the n-th sequence feature set U is recorded as the remaining sequence set corresponding to the n-th sequence feature set U; based on the remaining sequence set, all sets of sequences to be judged corresponding to the n-th sequence feature set U are obtained, and the i-th set of sequences to be judged corresponding to the n-th sequence feature set U is a new set formed by combining the i-th sequence in the remaining sequence set and the n-th sequence feature set U.

10. A microgrid intelligent control method for a digital power grid according to claim 9, characterized in that: A method for acquiring a feature sequence pair set corresponding to a sequence feature set and a feature sequence pair set corresponding to the sequence set to be determined, comprising: All parameter sequences in the sequence feature set are combined in pairs without repetition, and the set constructed by all sequence pairs obtained by the combination is recorded as the feature sequence pairs corresponding to the corresponding sequence feature set; all sequences in the sequence set to be judged are combined in pairs without repetition, and the set constructed by all sequence pairs obtained by the combination is recorded as the feature sequence pairs corresponding to the sequence set to be judged.

Images