Artificial intelligence assisted power flow calculation efficiency enhancement method and system

Abstract

The invention discloses an artificial intelligence-assisted power flow calculation efficiency enhancement method and system. The method comprises the steps of obtaining multiple electrical parameters in an AC power distribution network, a converter station and a DC power distribution network; and preprocessing the plurality of electrical parameters. According to the method, the voltage parameters and the current parameters in the AC power distribution network, the converter station and the DC power distribution network are acquired, and data are subjected to duplicate removal, abnormal value deletion and missing value filling, so that the stability of data analysis and the credibility of a result are improved, the completeness of a data set is ensured, and subsequent data fusion is facilitated; by classifying and fusing the data, the data are classified and divided into the electrical parameters of the AC power distribution network, the electrical parameters of the converter station and the electrical parameters of the DC power distribution network, so that the subsequent power flow calculation is more accurate, confusion and errors caused by excessive data are avoided, the requirements of workers are met, and the working efficiency is improved. And popularization and use are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of power flow calculation, and in particular to an artificial intelligence-assisted power flow calculation efficiency enhancement method and system. Background Art

[0002] The operating characteristics of an AC / DC hybrid distribution network containing a DC network are significantly different from those of a single AC or DC power grid. The operation and scheduling of an AC / DC hybrid distribution network is subject to multiple types of safety boundary conditions. Its power coordination and optimization strategy needs to comprehensively consider multiple factors such as the power grid topology, operating mode, flexible DC device control method, and network loss characteristics, which is technically difficult.

[0003] The existing calculation methods are all automated by computer. However, due to excessive data, such as the existence of multiple electrical parameters in the AC distribution network, converter station and DC distribution network in the system, the existing calculation processing system lacks data classification and fusion, which can easily lead to confusion of many data and incorrect calculation results, making it difficult to meet the needs of staff. Summary of the invention

[0004] In order to solve the above technical problems, an artificial intelligence-assisted method and system for enhancing the efficiency of power flow calculation are provided. This technical solution solves the problem that the existing computing and processing system proposed in the above background technology lacks data classification and fusion, which easily leads to confusion of a large amount of data and causes incorrect calculation results, making it difficult to meet the needs of staff.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An artificial intelligence-assisted method for enhancing the efficiency of power flow calculation, comprising:

[0007] Acquiring multiple electrical parameters in the AC power distribution network, the converter station and the DC power distribution network, the multiple electrical parameters including: electrical parameters of the AC power distribution network, electrical parameters of the converter station and electrical parameters of the DC power distribution network, the parameters being voltage and current;

[0008] Preprocessing multiple electrical parameters, including data deduplication, outlier deletion, and missing value filling, to obtain complete data;

[0009] Calculate the central tendency and dispersion of the complete data, divide the complete data into several groups, and merge the complete data of the same category;

[0010] The preset power flow calculation formula is retrieved from the database, and multiple integrated complete data are calculated to obtain the power flow data processing result.

[0011] Preferably, the data deduplication specifically includes the following steps:

[0012] Sending target data to be written to the first processor and the second processor respectively;

[0013] Based on the first processor, a hash calculation is performed on the target data to obtain a target hash fingerprint value corresponding to the target data;

[0014] Based on the second processor, determine whether the target hash fingerprint value has been stored in a preset hash fingerprint library, and if it has been stored, generate to-be-deleted state information corresponding to the target data, and send the to-be-deleted state information to the first processor;

[0015] Based on the first processor, the target data is deduplicated according to the state information to be deleted.

[0016] Preferably, the outlier deletion specifically comprises the following steps:

[0017] Retrieving a pre-set outlier matching model from a database;

[0018] Input each data into the outlier matching model to obtain the outlier value of each data;

[0019] Compare the obtained abnormal value with a first threshold value preset in the system;

[0020] If the abnormal value is greater than or equal to the first threshold, the data is determined to be abnormal data and deleted;

[0021] If the abnormal value is less than the first threshold, the data is determined to be normal data and no deletion operation is performed;

[0022] The outlier matching model is:

[0023]

[0024] Where C is the degree of fit between the characteristic parameters of the electrical parameter data and the characteristic parameters of the abnormal data set pre-set in the system, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0025] Preferably, the specific calculation formula for filling the missing values ​​is:

[0026]

[0027] Where D i is the filling data; i is the number of filling data; D j are different types of data; n is the number of different types of data.

[0028] Preferably, the calculation of the central tendency and dispersion degree of the complete data specifically comprises the following steps:

[0029] Calculate the mean value of the complete data and calculate the variance of the data according to the variance formula;

[0030] Setting the variance as the central tendency of the complete data and assigning a trend identification code to the central tendency;

[0031] Pair each data in the complete data with the remaining data in the complete data to obtain at least one paired group;

[0032] Calculate the absolute value of the difference between two data in each paired group of the complete data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value;

[0033] The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

[0034] Preferably, the calculation formula of the variance is as follows:

[0035]

[0036] Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

[0037] Preferably, the step of dividing the complete data into several groups and fusing the complete data of the same group specifically comprises the following steps:

[0038] Retrieve historical data classification criteria from the database, and obtain the range of the central tendency ratio and the range of the dispersion ratio in the classification criteria;

[0039] Calculate the ratio of the central tendency of the data to the mean of the central tendency of the sample data;

[0040] Calculate the ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data;

[0041] The first ratio and the second ratio are respectively compared with a second threshold and a third threshold preset in the system;

[0042] If the ratio 1 and the ratio are both less than or equal to the second threshold, it is determined to be the first classification;

[0043] If both ratio 1 and ratio 2 are greater than the second threshold but less than the third threshold, it is determined to be the second classification;

[0044] If both the ratio 1 and the ratio 2 are greater than or equal to the third threshold, it is determined to be the third category;

[0045] The data of the first category, the second category and the third category are fused to obtain the first category fused data, the second category fused data and the third category fused data.

[0046] Preferably, the power flow calculation formula is:

[0047] P AC =V AC I AC cos(θ)

[0048] Where P AC is power;

[0049] V AC and I AC are voltage and current respectively;

[0050] θ is the phase difference between voltage and current.

[0051] An artificial intelligence-assisted power flow calculation efficiency enhancement system, comprising:

[0052] An acquisition module, which is used to acquire multiple electrical parameters in an AC power distribution network, a converter station, and a DC power distribution network;

[0053] A data processing module, wherein a first processing unit and a second processing unit are integrated inside the data processing module;

[0054] A calculation module, which is used to retrieve a preset power flow calculation formula from a database, calculate multiple integrated complete data, and obtain a power flow data processing result;

[0055] A first processing unit, the first processing unit is used to pre-process multiple electrical parameters;

[0056] The second processing unit is used to calculate the central tendency and dispersion degree of the complete data, divide the complete data into several groups, and merge the complete data of the same category.

[0057] Compared with the prior art, the present invention provides an artificial intelligence-assisted method and system for enhancing the efficiency of power flow calculation, which has the following beneficial effects:

[0058] The present invention obtains voltage parameters and current parameters in the AC distribution network, converter station and DC distribution network, deduplicates the data, deletes outliers and fills in missing values, thereby improving the stability of data analysis and the credibility of the results, ensuring the integrity of the data set, and facilitating subsequent data fusion; the present invention classifies and fuses the data to classify the data into electrical parameters of the AC distribution network, electrical parameters of the converter station and electrical parameters of the DC distribution network, making the subsequent power flow calculation more accurate, avoiding confusion and errors caused by too much data, and meeting the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a method for enhancing the efficiency of power flow calculation in the present invention;

[0060] Figure 2 A schematic diagram of a method for deduplication of data in the present invention;

[0061] Figure 3 A schematic diagram of a method for deleting outliers in the present invention;

[0062] Figure 4 A schematic diagram of a method for filling missing values ​​in the present invention;

[0063] Figure 5 It is a schematic diagram of the method for calculating the central tendency and dispersion degree of complete data in the present invention. DETAILED DESCRIPTION

[0064] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0065] Example 1

[0066] Please refer to Figure 1-Figure 5 As shown, an artificial intelligence-assisted method for enhancing the efficiency of power flow calculation includes:

[0067] Acquire multiple electrical parameters in the AC distribution network, the converter station and the DC distribution network, the multiple electrical parameters include: electrical parameters of the AC distribution network, electrical parameters of the converter station and electrical parameters of the DC distribution network, the parameters are voltage and current;

[0068] Preprocess multiple electrical parameters, including data deduplication, outlier deletion, and missing value filling to obtain complete data;

[0069] Calculate the central tendency and dispersion of the complete data, divide the complete data into several groups, and merge the complete data of the same category;

[0070] The preset power flow calculation formula is retrieved from the database, and multiple integrated complete data are calculated to obtain the power flow data processing result.

[0071] It can be understood by those skilled in the art that the operation characteristics of an AC / DC hybrid distribution network including a DC network are significantly different from those of a single AC or DC power grid. The operation and scheduling of an AC / DC hybrid distribution network is subject to multiple types of safety boundary conditions. The present invention obtains voltage parameters and current parameters in an AC distribution network, a converter station and a DC distribution network, and performs data deduplication, outlier deletion and missing value filling. The purpose of data deduplication is to remove duplicate records to ensure that each data item appears only once in the data set. If deduplication is not performed, duplicate data may distort the analysis results. By removing outliers, the data can be made more consistent with common distributions, thereby improving the stability of data analysis and the credibility of results. By filling in missing values, the data set is ensured to be complete, thereby facilitating subsequent data fusion. The present invention classifies and fuses the data, so that the data is classified and divided into electrical parameters of an AC distribution network, electrical parameters of a converter station and electrical parameters of a DC distribution network, so that the subsequent power flow calculation is more accurate, avoiding confusion and errors caused by too much data, and meeting the needs of the staff.

[0072] Data deduplication specifically includes the following steps:

[0073] Sending target data to be written to the first processor and the second processor respectively;

[0074] Based on the first processor, a hash calculation is performed on the target data to obtain a target hash fingerprint value corresponding to the target data;

[0075] Based on the second processor, determine whether the target hash fingerprint value has been stored in a preset hash fingerprint library, and if it has been stored, generate to-be-deleted state information corresponding to the target data, and send the to-be-deleted state information to the first processor;

[0076] Based on the first processor, the target data is deduplicated according to the state information to be deleted.

[0077] The specific steps of outlier removal are as follows:

[0078] Retrieving a pre-set outlier matching model from a database;

[0079] Input each data into the outlier matching model to obtain the outlier value of each data;

[0080] Compare the obtained abnormal value with a first threshold value preset in the system;

[0081] If the abnormal value is greater than or equal to the first threshold, the data is determined to be abnormal data and deleted;

[0082] If the abnormal value is less than the first threshold, the data is determined to be normal data and no deletion operation is performed;

[0083] The outlier matching model is:

[0084]

[0085] Where C is the degree of fit between the characteristic parameters of the electrical parameter data and the characteristic parameters of the abnormal data set pre-set in the system, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0086] The specific calculation formula for missing value filling is:

[0087]

[0088] Where D i is the filling data; i is the number of filling data; D j are different types of data; n is the number of different types of data.

[0089] Calculating the central tendency and dispersion of complete data specifically includes the following steps:

[0090] Calculate the mean value of the complete data and calculate the variance of the data according to the variance formula;

[0091] Set the variance to the central tendency of the complete data and assign a trend identification code to the central tendency;

[0092] Pair each data in the complete data with the remaining data in the complete data to obtain at least one paired group;

[0093] Calculate the absolute value of the difference between two data in each paired group of the complete data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value;

[0094] Set the discrete value to the discrete degree of the data and assign a discrete identification code to the discrete degree.

[0095] The formula for calculating variance is as follows:

[0096]

[0097] Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

[0098] The complete data is divided into several groups and the integration of the complete data of the same category includes the following steps:

[0099] Retrieve historical data classification criteria from the database, and obtain the range of the central tendency ratio and the range of the dispersion ratio in the classification criteria;

[0100] Calculate the ratio of the central tendency of the data to the mean of the central tendency of the sample data;

[0101] Calculate the ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data;

[0102] The first ratio and the second ratio are respectively compared with a second threshold and a third threshold preset in the system;

[0103] If the ratio 1 and the ratio are both less than or equal to the second threshold, it is determined to be the first classification;

[0104] If both ratio 1 and ratio 2 are greater than the second threshold but less than the third threshold, it is determined to be the second classification;

[0105] If both the ratio 1 and the ratio 2 are greater than or equal to the third threshold, it is determined to be the third category;

[0106] The data of the first category, the second category and the third category are fused to obtain the first category fused data, the second category fused data and the third category fused data.

[0107] Power flow calculation formula:

[0108] P AC =V AC I AC cos(θ)

[0109] Where P AC is power;

[0110] V AC and I AC are voltage and current respectively;

[0111] θ is the phase difference between voltage and current.

[0112] An artificial intelligence-assisted power flow calculation efficiency enhancement system, comprising:

[0113] An acquisition module, which is used to acquire multiple electrical parameters in an AC distribution network, a converter station, and a DC distribution network;

[0114] A data processing module, wherein a first processing unit and a second processing unit are integrated inside the data processing module;

[0115] The calculation module is used to retrieve the preset power flow calculation formula from the database, calculate multiple integrated complete data, and obtain the power flow data processing result;

[0116] A first processing unit, the first processing unit is used to pre-process multiple electrical parameters;

[0117] The second processing unit is used to calculate the central tendency and the degree of dispersion of the complete data, and divide the complete data into several groups and categories, and merge the complete data of the same category.

[0118] Working principle and use process of the device: The present invention obtains voltage parameters and current parameters in the AC distribution network, converter station and DC distribution network, deduplicates the data, deletes outliers and fills missing values. The purpose of data deduplication is to remove duplicate records to ensure that each data appears only once in the data set. If duplicates are not removed, duplicate data may distort the analysis results; and by removing outliers, the data can be made more consistent with the common distribution, thereby improving the stability of data analysis and the credibility of the results; and by filling in missing values, the data set is guaranteed to be complete, thereby facilitating subsequent data fusion; the present invention classifies and fuses the data, so that the data is classified and divided into electrical parameters of the AC distribution network, electrical parameters of the converter station and electrical parameters of the DC distribution network, so that the subsequent power flow calculation is more accurate, avoiding confusion and errors caused by too much data, and meeting the needs of the staff.

[0119] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An artificial intelligence-assisted method for enhancing the efficiency of power flow calculation, characterized in that: include: Acquiring multiple electrical parameters in the AC power distribution network, the converter station and the DC power distribution network, the multiple electrical parameters including: electrical parameters of the AC power distribution network, electrical parameters of the converter station and electrical parameters of the DC power distribution network, the parameters being voltage and current; Preprocessing multiple electrical parameters, including data deduplication, outlier deletion, and missing value filling, to obtain complete data; Calculate the central tendency and dispersion of the complete data, divide the complete data into several groups, and merge the complete data of the same category; The preset power flow calculation formula is retrieved from the database, and multiple integrated complete data are calculated to obtain the power flow data processing result.

2. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 1, characterized in that: The data deduplication specifically includes the following steps: Sending target data to be written to the first processor and the second processor respectively; Based on the first processor, a hash calculation is performed on the target data to obtain a target hash fingerprint value corresponding to the target data; Based on the second processor, determine whether the target hash fingerprint value has been stored in a preset hash fingerprint library, and if it has been stored, generate to-be-deleted state information corresponding to the target data, and send the to-be-deleted state information to the first processor; Based on the first processor, the target data is deduplicated according to the state information to be deleted.

3. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 2, characterized in that: The outlier deletion specifically includes the following steps: Retrieving a pre-set outlier matching model from a database; Input each data into the outlier matching model to obtain the outlier value of each data; Compare the obtained abnormal value with a first threshold value preset in the system; If the abnormal value is greater than or equal to the first threshold, the data is determined to be abnormal data and deleted; If the abnormal value is less than the first threshold, the data is determined to be normal data and no deletion operation is performed; The outlier matching model is: Where C is the degree of fit between the characteristic parameters of the electrical parameter data and the characteristic parameters of the abnormal data set pre-set in the system, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

4. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 3, characterized in that: The specific calculation formula for filling missing values ​​is: Where D i is the filling data; i is the number of filling data; D j are different types of data; n is the number of different types of data.

5. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 4, characterized in that: The calculation of the central tendency and dispersion degree of the complete data specifically includes the following steps: Calculate the mean value of the complete data and calculate the variance of the data according to the variance formula; Setting the variance as the central tendency of the complete data and assigning a trend identification code to the central tendency; Pair each data in the complete data with the remaining data in the complete data to obtain at least one paired group; Calculate the absolute value of the difference between two data in each paired group of the complete data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value; The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

6. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 5, characterized in that: The calculation formula of the variance is as follows: Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

7. The method for enhancing the efficiency of power flow calculation assisted by artificial intelligence according to claim 6, characterized in that: The method of dividing the complete data into several groups and fusing the complete data of the same category specifically includes the following steps: Retrieve historical data classification criteria from the database, and obtain the range of the central tendency ratio and the range of the dispersion ratio in the classification criteria; Calculate the ratio of the central tendency of the data to the mean of the central tendency of the sample data; Calculate the ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data; The first ratio and the second ratio are respectively compared with a second threshold and a third threshold preset in the system; If the ratio 1 and the ratio are both less than or equal to the second threshold, it is determined to be the first classification; If both ratio 1 and ratio 2 are greater than the second threshold but less than the third threshold, it is determined to be the second classification; If both the ratio 1 and the ratio 2 are greater than or equal to the third threshold, it is determined to be the third category; The data of the first category, the second category and the third category are fused to obtain the first category fused data, the second category fused data and the third category fused data.

8. The artificial intelligence-assisted power flow calculation efficiency enhancement method according to claim 7, characterized in that: The power flow calculation formula is: P AC =V AC I AC cos(θ) Where P AC is power; V AC and I AC are voltage and current respectively; θ is the phase difference between voltage and current.

9. An artificial intelligence-assisted power flow calculation efficiency enhancement system, used to implement an artificial intelligence-assisted power flow calculation efficiency enhancement method as described in claims 1-8, characterized in that: include: An acquisition module, which is used to acquire multiple electrical parameters in an AC power distribution network, a converter station, and a DC power distribution network; A data processing module, wherein a first processing unit and a second processing unit are integrated inside the data processing module; The calculation module is used to retrieve a preset power flow calculation formula from a database, calculate multiple integrated complete data, and obtain a power flow data processing result.

10. The artificial intelligence-assisted power flow calculation efficiency enhancement system according to claim 9, characterized in that: include: A first processing unit, the first processing unit is used to pre-process multiple electrical parameters; The second processing unit is used to calculate the central tendency and dispersion degree of the complete data, divide the complete data into several groups, and merge the complete data of the same category.

Images