A method and system for constructing a digital twin distribution network operation portrait

Abstract

The present invention provides a method and system for constructing an operation portrait of a digital twin distribution network, comprising: constructing a distribution network evaluation index cloud data set based on the acquired digital twin distribution network load data, and calculating the membership of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set; calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set based on a preset distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model; calculating the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; the present invention forms a distribution network operation portrait with clear physical meaning, fine resolution granularity and objective evaluation basis; taking the label template as a benchmark, a scoring method is adopted to make the portrait characterization scale more refined.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and specifically relates to a method and system for constructing a digital twin distribution network operation portrait. Background Art

[0002] As new power systems with new energy as the main body are gradually formed, the uncertainty of the operation of sources, networks, and loads on the distribution side is becoming increasingly complex. User electricity consumption behavior will greatly affect the operation behavior of the distribution network. User electricity consumption behavior analysis plays an important role in power grid load forecasting, power consumption management, demand response, operation status analysis, and safety warning. Using digital twin technology to establish a collaborative interaction between virtual digital space and real physical space is an effective means to map the operation status of the distribution network and grasp the characteristics of distribution network behavior. Since user behavior changes with the seasons and external conditions, using digital twin technology to perceive user operation data in real time and dynamically capture user behavior characteristics is one of the typical application prospects of digital twin technology in power systems.

[0003] Since the electricity consumption behavior of a single user is not conducive to reflecting the operating characteristics of the distribution network due to its small individual capacity, scattered characteristics and large number of groups, it is more practical to draw a portrait based on the substation. However, the physical meaning of the operating portrait obtained in this way is unclear, the evaluation basis is highly subjective, and it cannot well describe the operating characteristics of the distribution network. Summary of the invention

[0004] In order to overcome the deficiencies of the above-mentioned prior art, the present invention proposes a method for constructing a digital twin distribution network operation portrait, comprising:

[0005] Based on the acquired digital twin distribution network load data, a distribution network evaluation index cloud data set is constructed, and according to the distribution network evaluation index cloud data set, the membership degree of the distribution network evaluation index cloud model is calculated;

[0006] Based on the preset distribution network evaluation index label template fuzzy power set and the membership degree of the distribution network evaluation index cloud model, calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set;

[0007] Based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set, a weighted score of the distribution network evaluation index cloud data set is calculated as an operation portrait of the digital twin distribution network;

[0008] The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator.

[0009] Preferably, the calculation of the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set based on the preset distribution network evaluation index label template fuzzy power set and the membership degree of the distribution network evaluation index cloud model includes:

[0010] Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set;

[0011] Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated.

[0012] Preferably, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated as follows:

[0013]

[0014] In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter;

[0015] Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows:

[0016] u i1 =min(u i3 ,u i4 ,u i5 ,u i6 )

[0017] u i2 =max(u i3 ,u i4 ,u i5 ,u i6 )

[0018] In the formula, u i3 and u i4 A r(u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system;

[0019] in:

[0020] u=x i (k)

[0021] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0022] Preferably, the weighted score of the distribution network evaluation index cloud data set is calculated as follows:

[0023]

[0024] In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

[0025] Preferably, calculating the degree of membership of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set includes:

[0026] Taking each data in the distribution network evaluation index cloud data set as a cloud droplet, using a reverse cloud generator, the cloud model expectation and entropy of each distribution network evaluation index are calculated;

[0027] According to the cloud model expectation and entropy of each distribution network evaluation index, the membership degree of the distribution network evaluation index cloud model is calculated.

[0028] Preferably, the membership degree of the distribution network evaluation index cloud model is calculated as follows:

[0029]

[0030] In the formula, B i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, Ex i is the expectation of the i-th distribution network evaluation index, En i is the entropy of the i-th distribution network evaluation index;

[0031] in:

[0032] u=x i (k)

[0033] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0034] Preferably, the cloud model expectation of each distribution network evaluation index is calculated as follows:

[0035]

[0036] Where, Ex i is the expectation of the i-th distribution network evaluation index, x i (k) is the value of the ith distribution network evaluation index on the kth day, and N is the total number of days;

[0037] The cloud model entropy of each distribution network evaluation index is calculated as follows:

[0038]

[0039] In the formula, En i is the entropy of the i-th distribution network evaluation index.

[0040] Preferably, the distribution network evaluation indicators include distribution network daily load rate, daily peak-to-valley difference rate, peak load rate, valley load rate, flat load rate, peak power contribution rate, and peak electricity contribution rate.

[0041] Based on the same inventive concept, the present invention also provides a digital twin distribution network operation portrait construction system, including: a cloud model module, a Hamming distance module and a weighted score module;

[0042] The cloud model module is used to construct a distribution network evaluation index cloud data set based on the acquired digital twin distribution network load data, and calculate the membership degree of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set;

[0043] The Hamming distance module is used to calculate the Hamming distance between the distribution network evaluation indicator cloud data set and the label template fuzzy power set based on the preset distribution network evaluation indicator label template fuzzy power set and the membership degree of the distribution network evaluation indicator cloud model;

[0044] The weighted score module is used to calculate the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set;

[0045] The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator.

[0046] Preferably, the Hamming distance module is specifically used for:

[0047] Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set;

[0048] Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated.

[0049] Preferably, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated as follows:

[0050]

[0051] In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter;

[0052] Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows:

[0053] u i1 =min(ui3 ,u i4 ,u i5 ,u i6 )

[0054] u i2 =max(u i3 ,u i4 ,u i5 ,u i6 )

[0055] In the formula, u i3 and u i4 A r (u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system;

[0056] in:

[0057] u=x i (k)

[0058] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0059] Preferably, the weighted score of the distribution network evaluation index cloud data set is calculated as follows:

[0060]

[0061] In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

[0062] Preferably, the cloud model module is specifically used for:

[0063] Taking each data in the distribution network evaluation index cloud data set as a cloud droplet, using a reverse cloud generator, the cloud model expectation and entropy of each distribution network evaluation index are calculated;

[0064] According to the cloud model expectation and entropy of each distribution network evaluation index, the membership degree of the distribution network evaluation index cloud model is calculated.

[0065] Compared with the closest prior art, the present invention has the following beneficial effects:

[0066] The present invention provides a method and system for constructing an operation portrait of a digital twin distribution network, comprising: constructing a distribution network evaluation index cloud data set based on the acquired digital twin distribution network load data, and calculating the membership of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set; calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set based on a preset distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model; calculating the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; wherein the score of the distribution network evaluation index label template fuzzy power set represents the operation quality of the distribution network evaluation index under the indicator; the present invention performs weighted summation with the fuzzy distance between the operation indicator and the label template according to the score of the label template to obtain the scoring value of the operation indicator, thereby forming a distribution network operation portrait with clear physical meaning, fine resolution granularity and objective evaluation basis. Based on the label template, each indicator portrait is characterized by scoring, which can make the portrait depiction more refined.

[0067] The present invention can effectively extract the macroscopic operation characteristics of the distribution network in different time domains, and the formed operation portrait can effectively characterize and analyze the general operation laws of the distribution network in the time domain; the membership degree is constructed for the label template to make the judgment more objective and operational, and the results are objective and practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A schematic diagram of a process flow of a method for constructing a digital twin distribution network operation portrait provided by the present invention;

[0069] Figure 2 A flowchart of an embodiment of a method for constructing an operation portrait of a digital twin distribution network provided by the present invention;

[0070] Figure 3 A distribution network structure diagram of an embodiment of a method for constructing a digital twin distribution network operation portrait provided by the present invention;

[0071] Figure 4 A schematic diagram of a daily load curve of a distribution network area 1 according to an embodiment of a method for constructing a digital twin distribution network operation portrait provided by the present invention;

[0072] Figure 5 A schematic diagram of the scores of various indicators of the distribution network area 1 in an embodiment of a method for constructing a digital twin distribution network operation portrait provided by the present invention;

[0073] Figure 6 A schematic diagram of the basic structure of a digital twin distribution network operation portrait construction system provided by the present invention. DETAILED DESCRIPTION

[0074] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings.

[0075] Embodiment 1:

[0076] The present invention provides a method for constructing a digital twin distribution network operation portrait, and its flow chart is as follows: Figure 1 As shown, including:

[0077] Step 1: Based on the acquired digital twin distribution network load data, a distribution network evaluation index cloud data set is constructed, and according to the distribution network evaluation index cloud data set, the membership degree of the distribution network evaluation index cloud model is calculated;

[0078] Step 2: Based on the preset distribution network evaluation index label template fuzzy power set and the membership degree of the distribution network evaluation index cloud model, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated;

[0079] Step 3: Based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set, calculate the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network;

[0080] The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator.

[0081] The purpose of the present invention is to provide a method for constructing a digital twin distribution network operation portrait, adopt an objective statistical method for the distribution network operation big data, extract the macroscopic operation characteristics of the distribution network in different time domains, and obtain a distribution network operation portrait with clear physical meaning, fine depiction scale, and objective evaluation basis.

[0082] The present invention provides a method for constructing a digital twin distribution network operation portrait, which specifically includes the following steps:

[0083] 1) Obtain distribution network load data and construct a distribution network load data sample set;

[0084] 2) According to the distribution network load data sample set, calculate the distribution network daily load rate, daily peak-to-valley difference rate, peak load rate, valley load rate, flat load rate, peak power contribution rate, peak electricity contribution rate and other distribution network evaluation index data;

[0085] 3) Constructing a distribution network evaluation index cloud data set based on the distribution network evaluation index data;

[0086] 4) Calculate the cloud model expectation, entropy and super entropy values ​​of the distribution network evaluation index data according to the distribution network evaluation index data;

[0087] 5) Calculating the membership of the cloud model according to the cloud model expectation, entropy and super entropy values;

[0088] 6) Calculate the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set;

[0089] 7) Calculate the weighted score of the distribution network evaluation index cloud data set.

[0090] Step 1 specifically includes:

[0091] 1) Based on the distribution network load data, construct a distribution network load data sample set:

[0092] X=(X1,X2,…,X k ,…,X N ) (1)

[0093] Where, X k is the load data sample set of the kth day in units of days, k = 1, 2, ..., N, and the total number of distribution network load data samples is N;

[0094] The distribution network collects load data every 15 minutes during the day, so we have:

[0095] X k =(P k (1),P k (2),…,P k (96)). (2)

[0096] 2) According to the distribution network load data sample set, the distribution network daily load rate, daily peak-to-valley difference rate, peak load rate, valley load rate, flat load rate, peak power contribution rate, peak electricity contribution rate and other distribution network evaluation index data of the kth day are calculated according to formulas (3) to (9), including:

[0097]

[0098] Where x1(k) is the daily load rate of the distribution network on the kth day, P k(t) is the load power value at time t on the kth day, P k.N is the rated power of the load in the area on the kth day, and T is the duration of the whole day;

[0099] x2(k)=(P k.max -P k.min ) / P k.N (4)

[0100] Where x2(k) is the peak-to-valley difference rate of the distribution network on the kth day, P k.max and P k.min are the maximum and minimum load powers of the substation on the kth day respectively;

[0101]

[0102] In the formula, x3(k) is the peak load rate of the distribution network on the kth day, t1 is the start time of the daily load peak, and t2 is the end time of the daily load peak;

[0103]

[0104] Where x4(k) is the valley load rate of the distribution network on the kth day, t3 is the start time of the daily load valley, and t4 is the end time of the daily load valley;

[0105]

[0106] Where x5(k) is the average load rate of the distribution network on the kth day, t5 is the start time of the daily load average period, and t6 is the end time of the daily load average period;

[0107] x6(k)=(P k.pk -P k.ave ) / P k.N (8)

[0108] Where x6(k) is the peak power contribution rate of the distribution network on the kth day, P k.pk and P k.ave are the peak and average power of the load in the area on the kth day respectively;

[0109]

[0110] In the formula, x7(k) is the peak power contribution rate of the distribution network on the kth day, t7 is the start time of the daily load peak, and t8 is the end time of the daily load peak;

[0111] Among them, the peak periods are: 09:00-12:00, 14:30-17:30, 19:00-22:00; the valley periods are: 22:00-24:00 and 00:00-06:00; and the rest are normal periods.

[0112] 3) The distribution network evaluation indicators are divided into benefit indicators and cost indicators. The distribution network daily load rate, valley load rate, and flat load rate are benefit indicators, while the daily peak-valley difference rate, peak load rate, peak power contribution rate, and peak electricity contribution rate are cost indicators.

[0113] The distribution network evaluation index cloud dataset B is constructed based on the daily distribution network evaluation index values:

[0114] B=(B1,B2,…,B i ,…,B7) (10)

[0115] In the formula, B i is the distribution network evaluation index cloud data subset, B i =(x i (1),x i (2),…,x i (k),…,x i (N)), i=1,2,…,7.

[0116] Determining the distribution network evaluation index membership parameter according to the distribution network evaluation index cloud data set includes:

[0117] The membership parameters of benefit-type indicators are b1, b2, b3, and b4;

[0118] The membership parameters of cost-type indicators are c1, c2, c3, and c4;

[0119] Sort the distribution network evaluation indicators in the distribution network evaluation indicator cloud data set from small to large:

[0120] For benefit-based indicators, the distribution network evaluation indicator cloud data set is sorted from small to large. After sorting, the largest value in the top 10% of all data is determined as b1; the largest value in 10% to 40% is determined as b2; the largest value in 40% to 70% is determined as b3; the largest value in 70% to 100% is determined as b4;

[0121] For cost-type indicators, the distribution network evaluation indicator cloud data set is sorted from small to large. After sorting, the largest value in the first 10% of all data is determined as c1; the largest value in 10% to 40% is determined as c2; the largest value in 40% to 70% is determined as c3; and the largest value in 70% to 100% is determined as c4.

[0122] 4) Using the data in the distribution network evaluation index cloud data set as cloud droplets, applying the reverse cloud generator, and calculating the cloud model expectation, entropy and super entropy values ​​of each distribution network evaluation index according to formula (11) to formula (13), including:

[0123]

[0124] Where, Ex i is the expectation of the i-th distribution network evaluation index, i = 1, 2, ..., 7;

[0125]

[0126] In the formula, En i is the entropy of the i-th distribution network evaluation index;

[0127]

[0128] In the formula, He i is the super entropy of the i-th distribution network evaluation index, is the variance of the i-th distribution network evaluation index.

[0129] 5) According to the expectation, entropy and super entropy values ​​of the distribution network evaluation index cloud data set, the i-th distribution network evaluation index cloud data subset B is obtained according to formula (14): i The membership function of is:

[0130]

[0131] Where u = x i (k).

[0132] Step 2 specifically includes:

[0133] Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set;

[0134] 6) Construct label template fuzzy power set A r , including: A r is the fuzzy power set of label templates representing “excellent, good, medium, and poor” respectively, r=1,2,3,4;

[0135] If indicator u is a benefit indicator, A r The membership function A r (u) can be expressed as:

[0136]

[0137]

[0138]

[0139]

[0140] If the indicator u is a cost indicator, A r The membership function A r (u) can be expressed as:

[0141]

[0142]

[0143]

[0144]

[0145] Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated, including:

[0146] According to formula (15), the distribution network evaluation index cloud data subset B is calculated i Fuzzy power set A with label template r Hamming distance

[0147]

[0148] In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter;

[0149] Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows:

[0150] u i1 =min(u i3 ,u i4 ,u i5 ,u i6 )

[0151] u i2 =max(u i3 ,u i4 ,u i5 ,u i6 )

[0152] In the formula, ui3 and u i4 A r (u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system;

[0153] in:

[0154] u=x i (k)

[0155] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0156] Step 3 specifically includes:

[0157] 7) Calculate the weighted score of the distribution network evaluation index cloud data set according to formula (16):

[0158]

[0159] In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

[0160] As can be seen from the above, the present invention provides a method for constructing a digital twin distribution network operation portrait, establishes an index system that reflects the operation load of distribution station areas and lines, and uses an objective method of statistical sorting to divide the characteristic indicators into fuzzy label templates; using daily operation indicators as cloud droplets, based on annual, seasonal, and monthly multi-time domain big data, the reverse cloud generator is used to form a fuzzy representation of the operation indicators; according to the score framework of the label template, the fuzzy distance between the operation indicator and the label template is weighted and summed to obtain the score value of the operation indicator, forming a distribution network operation portrait with clear physical meaning, fine resolution granularity, and objective evaluation basis. Form a distribution network operation portrait with clear physical meaning, fine depiction scale, and objective evaluation basis. Different from the existing technology, the present invention uses a reverse cloud generator to conceptualize modeling of the twin distribution network operation big data, which can effectively extract the macro operation characteristics of the distribution network in different time domains. The operation portrait can effectively characterize and analyze the general operation laws of the distribution network in the time domain; based on the label template, each indicator portrait is characterized by scoring, which can make the portrait resolution granularity more detailed; the membership of the label template is constructed according to the sample ranking percentage, so that the physical meaning of the portrait is clear, the judgment is more objective and operational, and the physical meaning is clear, and the results are objective and practical.

[0161] Embodiment 2:

[0162] This embodiment introduces the specific implementation process of a method for constructing a digital twin distribution network operation portrait. Figure 2 As shown, including:

[0163] The embodiment of the present invention is studied in combination with an actual distribution network system. Figure 3 The corresponding line parameters are shown in Table 1. The rated capacity of the distribution substations is 400kVA, and the maximum transmission capacity of the lines is equal, both 6MVA. The load data of a certain area from January 1, 2009 to December 31, 2014, a total of 2190 days, are selected, with one sampling point every 15 minutes, and 96 points a day. 33 groups of daily load data are randomly selected as the typical load curves of 33 substations. For example, the daily load curve of substation 1 is as follows Figure 4 As shown. The characteristic indicators of each of the 33 substations were calculated for their daily load data, and 7 sets of indicator data were obtained for each substation. The indicator data of substation 1 are shown in Table 2. Due to space limitations, the other substations are not listed. For each of the 7 indicators of each substation, a random number was drawn from the range of -15% to +15% with equal probability. 3,000 groups were drawn from each substation to form 3,000 samples or cloud droplets. A total of 99,000 samples from 33 substations were sorted to obtain the membership parameters of benefit-type indicators and cost-type indicators, as shown in Table 2.

[0164] The characteristic indicators of 3000 groups of samples randomly generated in each substation are input into the reverse cloud generator to obtain the cloud model parameters of the indicators. The cloud model parameters of various indicators of substation 1 are obtained as shown in Table 3.

[0165] Substituting the above data into equations (15) and (16), we can obtain the scores of each indicator in area 1, as follows: Figure 5 Similarly, the scores of each indicator of other substations can be obtained, thus forming an operation profile of each substation.

[0166] Table 1 Distribution network line parameters

[0167]

[0168] Table 2 Membership parameters of benefit-based indicators and cost-based indicators in Area 1

[0169]

[0170]

[0171] Table 3 Cloud model parameters of each indicator in area 1 and the score values ​​of each indicator

[0172]

[0173] Embodiment 3:

[0174] Based on the same inventive concept, the present invention also provides a digital twin distribution network operation portrait construction system, such as Figure 6 As shown, it includes: a cloud model module, a Hamming distance module and a weighted score module;

[0175] The cloud model module is used to construct a distribution network evaluation index cloud data set based on the acquired digital twin distribution network load data, and calculate the membership degree of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set;

[0176] The Hamming distance module is used to calculate the Hamming distance between the distribution network evaluation indicator cloud data set and the label template fuzzy power set based on the preset distribution network evaluation indicator label template fuzzy power set and the membership degree of the distribution network evaluation indicator cloud model;

[0177] The weighted score module is used to calculate the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set;

[0178] The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator.

[0179] The Hamming distance module is specifically used for:

[0180] Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set;

[0181] Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated.

[0182] The Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated as follows:

[0183]

[0184] In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter;

[0185] Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows:

[0186] u i1 =min(u i3 ,u i4 ,u i5 ,u i6 )

[0187] u i2 =max(u i3 ,u i4 ,u i5 ,u i6 )

[0188] In the formula, u i3 and u i4 A r (u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system;

[0189] in:

[0190] u=x i (k)

[0191] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0192] The weighted score of the distribution network evaluation index cloud data set is calculated as follows:

[0193]

[0194] In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

[0195] The cloud model module is specifically used for:

[0196] Taking each data in the distribution network evaluation index cloud data set as a cloud droplet, using a reverse cloud generator, the cloud model expectation and entropy of each distribution network evaluation index are calculated;

[0197] According to the cloud model expectation and entropy of each distribution network evaluation index, the membership degree of the distribution network evaluation index cloud model is calculated.

[0198] The membership degree of the distribution network evaluation index cloud model is calculated as follows:

[0199]

[0200] In the formula, B i (u) is the subset B in the distribution network evaluation index cloud dataset iThe cloud model membership function, Ex i is the expectation of the i-th distribution network evaluation index, En i is the entropy of the i-th distribution network evaluation index;

[0201] in:

[0202] u=x i (k)

[0203] In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

[0204] The cloud model expectation of each distribution network evaluation index is calculated as follows:

[0205]

[0206] Where, Ex i is the expectation of the i-th distribution network evaluation index, x i (k) is the value of the ith distribution network evaluation index on the kth day, and N is the total number of days;

[0207] The cloud model entropy of each distribution network evaluation index is calculated as follows:

[0208]

[0209] In the formula, En i is the entropy of the i-th distribution network evaluation index.

[0210] The distribution network evaluation indicators include distribution network daily load rate, daily peak-to-valley difference rate, peak load rate, valley load rate, normal load rate, peak power contribution rate, and peak electricity contribution rate.

[0211] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0212] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0213] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0214] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims of the invention.

Claims

1. A method for constructing a digital twin distribution network operation portrait, characterized in that: include: Based on the acquired digital twin distribution network load data, a distribution network evaluation index cloud data set is constructed, and according to the distribution network evaluation index cloud data set, the membership degree of the distribution network evaluation index cloud model is calculated; Based on the preset distribution network evaluation index label template fuzzy power set and the membership degree of the distribution network evaluation index cloud model, calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; Based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set, a weighted score of the distribution network evaluation index cloud data set is calculated as an operation portrait of the digital twin distribution network; The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator; The method of calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set based on the preset distribution network evaluation index label template fuzzy power set and the membership degree of the distribution network evaluation index cloud model includes: Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set; Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; The Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated as follows: In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter; Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows: u i1 =min(u i3 ,u i4 ,u i5 ,u i6 ) u i2 =max(u i3 ,u i4 ,u i5 ,u i6 ) In the formula, u i3 and u i4 A r (u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system; in: u=x i (k) In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day; The weighted score of the distribution network evaluation index cloud data set is calculated as follows: In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

2. The method according to claim 1, characterized in that The calculating the degree of membership of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set includes: Taking each data in the distribution network evaluation index cloud data set as a cloud droplet, using a reverse cloud generator, the cloud model expectation and entropy of each distribution network evaluation index are calculated; According to the cloud model expectation and entropy of each distribution network evaluation index, the membership degree of the distribution network evaluation index cloud model is calculated.

3. The method according to claim 1 or 2, characterized in that The membership degree of the distribution network evaluation index cloud model is calculated as follows: In the formula, B i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, Ex i is the expectation of the i-th distribution network evaluation index, En i is the entropy of the i-th distribution network evaluation index; in: u=x i (k) In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day.

4. The method according to claim 2, characterized in that The cloud model expectation of each distribution network evaluation index is calculated as follows: Where, Ex i is the expectation of the i-th distribution network evaluation index, x i (k) is the value of the ith distribution network evaluation index on the kth day, and N is the total number of days; The cloud model entropy of each distribution network evaluation index is calculated as follows: In the formula, En i is the entropy of the i-th distribution network evaluation index.

5. The method according to claim 1, characterized in that The distribution network evaluation indicators include distribution network daily load rate, daily peak-to-valley difference rate, peak load rate, valley load rate, normal load rate, peak power contribution rate, and peak electricity contribution rate.

6. A digital twin distribution network operation portrait construction system, characterized in that: include: Cloud model module, Hamming distance module and weighted score module; The cloud model module is used to construct a distribution network evaluation index cloud data set based on the acquired digital twin distribution network load data, and calculate the membership degree of the distribution network evaluation index cloud model according to the distribution network evaluation index cloud data set; The Hamming distance module is used to calculate the Hamming distance between the distribution network evaluation indicator cloud data set and the label template fuzzy power set based on the preset distribution network evaluation indicator label template fuzzy power set and the membership degree of the distribution network evaluation indicator cloud model; The weighted score module is used to calculate the weighted score of the distribution network evaluation index cloud data set as the operation portrait of the digital twin distribution network based on the score of the preset distribution network evaluation index label template fuzzy power set and the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; The score of the fuzzy power set of the distribution network evaluation indicator label template represents the operation quality of the distribution network evaluation indicator under the indicator; The Hamming distance module is specifically used for: Based on the preset distribution network evaluation index label template fuzzy power set, calculating the membership degree of the distribution network evaluation index label template fuzzy power set; Based on the membership of the distribution network evaluation index label template fuzzy power set and the membership of the distribution network evaluation index cloud model, calculating the Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set; The Hamming distance between the distribution network evaluation index cloud data set and the label template fuzzy power set is calculated as follows: In the formula, D(A r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of i (u) is the subset B in the distribution network evaluation index cloud dataset i The cloud model membership function, A r (u) is the fuzzy power set A of the distribution network evaluation index label template r The membership degree of the distribution network is i, i is the i-th distribution network evaluation index, r is the r-th distribution network evaluation index label template, u i1 is the first parameter, u i2 is the second parameter; Among them, the first parameter u i1 and the second parameter u i2 , expressed as follows: u i1 =min(u i3 ,u i4 ,u i5 ,u i6 ) u i2 =max(u i3 ,u i4 ,u i5 ,u i6 ) In the formula, u i3 and u i4 A r (u) intersection with the horizontal axis of the coordinate system, u i5 and u i6 For B i (u) intersection with the horizontal axis of the coordinate system; in: u=x i (k) In the formula, x i (k) is the evaluation index value of the ith distribution network on the kth day; The weighted score of the distribution network evaluation index cloud data set is calculated as follows: In the formula, G(B i ) is a subset B in the distribution network evaluation index cloud dataset i The weighted score of s ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template s The Hamming distance of r ,B i ) is a subset B in the distribution network evaluation index cloud dataset i Fuzzy power set A of distribution network evaluation index label template r The Hamming distance of r ,A s ) is the adjacent distribution network evaluation index label template fuzzy power set A r With A s The distance between them, r and s are the rth and sth distribution network evaluation index label templates respectively, G(A r ) and G(A s ) are the fuzzy power set A of the distribution network evaluation index label template r and A s score.

7. The system according to claim 6, characterized in that The cloud model module is specifically used for: Taking each data in the distribution network evaluation index cloud data set as a cloud droplet, using a reverse cloud generator, the cloud model expectation and entropy of each distribution network evaluation index are calculated; According to the cloud model expectation and entropy of each distribution network evaluation index, the membership degree of the distribution network evaluation index cloud model is calculated.

Images