A Fast Construction Method for a Power Data Analysis Model Based on Big Data

Abstract

The present invention relates to the field of model construction technology, specifically a method for quickly constructing an electric power data analysis model based on big data, comprising the following steps: based on the voltage, current and power data of the substation, monitoring the voltage amplitude, frequency offset and phase angle error, detecting data integrity, removing abnormal data node information, and obtaining electric power data processing results. In the present invention, by enhancing the verification of data integrity and the accurate extraction of key features, the prediction accuracy of electric power demand is optimized, and by combining data backtracking and hash comparison, the reliability of data is ensured. Through in-depth analysis of power load characteristics and equipment operating parameters, the quality of data input is improved, thereby optimizing the analysis of power system behavior. By dynamically adjusting the weight of power input data to match actual usage trends, the application flexibility and real-time response capability of the data analysis model are enhanced, thereby optimizing resource allocation and power generation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of model construction technology, and in particular to a method for quickly constructing an electric power data analysis model based on big data. Background Art

[0002] Model building refers to the creation of a mathematical or simulation model to imitate real-world processes, systems or phenomena. It is mainly used for prediction, optimization and decision support. It is a core component of fields such as data science, artificial intelligence and machine learning. In the power industry, model building focuses on how to use the large amount of collected electricity usage data to predict electricity demand, optimize power generation and allocation resources, and improve the energy efficiency and reliability of the system.

[0003] Among them, the rapid construction method of the big data power data analysis model aims to quickly develop a model that can process and analyze large-scale power data sets, so as to use power data to conduct in-depth research on the energy use of rural enterprises, with special attention to collecting the electricity usage data of enterprises in a specific time period to calculate the output value per kilowatt-hour, which helps to provide necessary data support for the energy-saving transformation of high-energy-consuming equipment and provide intelligent diagnosis services for power equipment for high-voltage enterprise customers. In addition, the model also supports real-time energy consumption analysis, accurately monitors the production safety status of the production area, establishes a power consumption tracking ledger, and specifically monitors the power load of agricultural product enterprises to promptly assist in meeting the power demand in production.

[0004] Existing technologies have deficiencies in data integrity verification and dynamic adjustment mechanisms, which limit the accuracy of power demand forecasts and the efficiency of resource allocation. The lack of an effective data verification mechanism makes it difficult to detect and correct data errors in a timely manner, affecting the accuracy of power data analysis. In addition, existing methods have not fully realized their potential in using power load characteristics and equipment operating parameters for model optimization, resulting in the inability to accurately predict power demand during peak demand periods. This insufficient prediction can easily lead to uneven distribution of power resources, affecting production efficiency and the stability of the power system. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a method for quickly constructing an electric power data analysis model based on big data.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for rapidly constructing a power data analysis model based on big data, comprising the following steps:

[0007] S1: Based on the substation voltage, current, and power data, the voltage amplitude, frequency offset, and phase angle error are monitored to check data integrity, remove abnormal data node information, and obtain power data processing results;

[0008] S2: Based on the power data processing results, collect power load characteristics, equipment operating parameters and time series data, evaluate the interdependence between each characteristic, screen key characteristics of the power system, and obtain a balanced configuration of power characteristics;

[0009] S3: Based on the power characteristic balancing configuration, calculate the power change rate within the difference time window, select the time interval of power demand growth, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, and obtain the power growth trend dynamic indicator;

[0010] S4: Analyze the load parameters of the transmission lines and the power supply status of the power grid zones based on the power growth trend dynamic indicators, determine the power supply and demand status of each zone, and obtain supply and demand balance assessment data;

[0011] S5: Call the supply and demand balance assessment data, analyze and select the most efficient power generation unit, and then combine it with the real-time load and power forecast data of the power grid to obtain a power analysis deployment-ready model.

[0012] The improvements of the present invention are that the power data processing results include data integrity records and abnormal node indexes; the power feature balancing configuration is specifically a load feature set, an equipment parameter set, and a time series set; the power growth trend dynamic indicators include rate change analysis results, growth interval identification results, and data weights; the supply and demand balance evaluation data are specifically load status information, prediction error evaluation results, and analysis parameter details; the power analysis deployment-ready model includes power generation efficiency data, cost-effectiveness data, and load response configuration.

[0013] The present invention is improved in that the steps of obtaining the power data processing results are specifically as follows:

[0014] S111: Based on the voltage, current, and power data of the substation, the voltage amplitude, frequency offset, and phase angle error are monitored, the amplitude offset rate, frequency error, and phase angle change of the data nodes are calculated, and the data nodes that exceed the standard range are screened to obtain the abnormal data node set;

[0015] S112: Calling the abnormal data node set, using the data backtracking mechanism to restore missing data information from the backup system, performing hash value comparison, screening data nodes with unmatched hash values, and obtaining a data integrity abnormal point set;

[0016] S113: Call the data integrity abnormal point set, remove abnormal data nodes, evaluate voltage amplitude, frequency offset and phase angle error, and use the formula: ;

[0017] Calculate data quality assessment values , and screen qualified data nodes according to the evaluation value to obtain the power data processing results, among which, Representative The voltage amplitude of each data node, represents the voltage reference value, Representative The frequency of data nodes, represents the frequency reference value, Representative The phase angle of the data node, represents the phase angle reference value, Represents the total number of data nodes, represents the standard deviation of the voltage data, represents the standard deviation of frequency data, Represents the standard deviation of the phase angle data.

[0018] The present invention is improved in that the steps of obtaining the power feature balancing configuration are specifically as follows:

[0019] S211: Based on the power data processing results, collect power load characteristics, equipment operating parameters and time series data, extract the load power, equipment current and voltage change trends of each data point, and analyze the distribution of characteristics in the time dimension to obtain the power characteristic time series distribution;

[0020] S212: Based on the power feature time series distribution, calculate the correlation coefficient between each feature, screen the key features of mutual dependence, and analyze their correlation with the power system operation state to obtain the power key feature set;

[0021] S213: Call the power key feature set, reformat the feature representation, and use the formula based on the standardized mean and feature deviation: ;

[0022] Calculating feature balance , and adjust the feature normalization parameters to obtain the power feature balancing configuration, where Representative Power characteristic values, Representative characteristics The mean of Representative characteristics The standard deviation of Represents the total number of feature data points.

[0023] The present invention is improved in that the steps for obtaining the dynamic indicator of power growth trend are specifically as follows:

[0024] S311: Based on the power feature balancing configuration, analyze the power load curve, calculate the power change rate within the difference time window, continuously detect the power change value, and calculate the average power change rate at each time interval to generate power change data;

[0025] S312: Calculating a rate increment value based on the power change data, setting a dynamic screening threshold, screening time intervals where the rate increment exceeds the threshold, and obtaining a set of power demand growth intervals;

[0026] S313: Call the power demand growth interval set, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, match the current power usage trend, and use the formula: ;

[0027] Get dynamic indicators of electricity growth trends ,in, Represents the change in power input data, Represents the total number of power data points in the time interval, represents the weight coefficient of the power input data, Represents the fluctuation offset of the power load curve within the target time interval, represents the total number of data points in the fluctuation analysis, An adjustment factor representing the shift in trend.

[0028] The present invention is improved in that the steps of obtaining the supply and demand balance assessment data are specifically as follows:

[0029] S411: Analyze transmission line load parameters based on the power growth trend dynamic indicator, normalize the power transfer ratio of each group of transmission lines, and obtain a transmission line load ratio;

[0030] S412: Calculating the supply-demand deviation value of each power grid zone based on the transmission line load ratio and the power supply capacity parameter of the power grid zone, and determining the current power supply status to obtain the power grid zone supply-demand deviation value;

[0031] S413: Based on the power grid partition supply and demand deviation, determine the supply and demand forecast error, optimize the analysis parameters, and use the formula: ;

[0032] Calculate the supply and demand balance error value , and compare the adjusted forecast data with the current data to obtain the supply and demand balance assessment data, among which, Representative The actual load demand of each grid zone, Representative The power supply capacity of each grid section, Represents the total number of grid partitions.

[0033] The present invention is improved in that the steps of obtaining the power analysis deployment-ready model are specifically as follows:

[0034] S511: Calling the supply and demand balance assessment data, assessing the power demand level, obtaining the power generation capacity of the power generation unit, and analyzing the degree of matching between the power generation capacity and the demand level to obtain the power supply and demand matching degree;

[0035] S512: Based on the power supply and demand matching degree and combined with the power generation cost data of the power generation units, the unit power generation cost is calculated, and the power generation unit with the best power generation cost is selected using the formula: ;

[0036] Calculating unit efficiency coefficient ,in, Representative The power generation of each power generation unit, Representative The power generation cost of each power generation unit, Representative The power demand in each time period, Represents the total number of all time periods;

[0037] S513: Based on the unit efficiency coefficient, combined with the screened power generation units, and according to the real-time load and power forecast data of the power grid, an executable model file is created to obtain a power analysis deployment-ready model.

[0038] Compared with the prior art, the advantages and positive effects of the present invention are:

[0039] In the present invention, the prediction accuracy of power demand is optimized by enhancing the verification of data integrity and the accurate extraction of key features. The reliability of data is ensured by combining data backtracking and hash comparison. The quality of data input is improved through in-depth analysis of power load characteristics and equipment operating parameters, thereby optimizing the analysis of power system behavior. By dynamically adjusting the weight of power input data to match actual usage trends, the application flexibility and real-time response capability of the data analysis model are enhanced, thereby optimizing resource allocation and power generation efficiency, which not only improves the utilization efficiency of power resources, but also ensures the energy security and efficiency of power production. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention proposes a flowchart of a method for rapidly constructing a power data analysis model based on big data;

[0041] Figure 2 This is a flow chart for obtaining power data processing results in the present invention;

[0042] Figure 3A flowchart for obtaining the power feature balancing configuration in the present invention;

[0043] Figure 4 This is a flow chart for obtaining the dynamic indicator of power growth trend in the present invention;

[0044] Figure 5 This is a flow chart for obtaining supply and demand balance assessment data in the present invention;

[0045] Figure 6 A flowchart for obtaining a deployment-ready model for power analysis in the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined. Example

[0048] See also Figure 1 The present invention provides a technical solution: a method for quickly constructing a power data analysis model based on big data, comprising the following steps:

[0049] S1: Based on the substation's voltage, current, and power data, the system monitors voltage amplitude, frequency offset, and phase angle error. It then uses a data backtracking mechanism to recover missing data from the backup system, performs a hash value comparison to check data integrity, and removes abnormal data node information to obtain power data processing results.

[0050] S2: Based on the power data processing results, collect power load characteristics, equipment operating parameters and time series data, evaluate the interdependence between each characteristic, and screen the key characteristics of the power system, reformat the characteristic representation, and obtain the power characteristic balance configuration;

[0051] S3: Based on the balanced configuration of power characteristics, analyze the power load curve, calculate the power change rate within the differential time window, select the time interval with power demand growth, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, match the current power usage trend, and obtain the dynamic indicator of power growth trend;

[0052] S4: Based on the dynamic indicators of power growth trends, analyze the load parameters of transmission lines and the power supply status of power grid zones, determine the power supply and demand status of each zone, determine the supply and demand forecast error, optimize the analysis parameters, and then compare the adjusted forecast data with the current data to obtain supply and demand balance assessment data;

[0053] S5: Call supply and demand balance assessment data, collect available power generation parameters and power generation cost data, analyze and select the most efficient power generation units (power plants or generator sets), and then combine them with real-time grid load and power forecast data to create an executable model file to obtain a power analysis deployment-ready model.

[0054] The power data processing results include data integrity records and abnormal node indexes. The power feature balancing configuration specifically includes load feature sets, equipment parameter sets, and time series sets. The dynamic indicators of power growth trends include rate change analysis results, growth interval identification results, and data weights. The supply and demand balance assessment data specifically includes load status information, prediction error assessment results, and analysis parameter details. The power analysis deployment-ready model includes power generation efficiency data, cost-effectiveness data, and load response configuration.

[0055] See also Figure 2 , the specific steps for obtaining the power data processing results are:

[0056] S111: Based on the voltage, current, and power data of the substation, the voltage amplitude, frequency offset, and phase angle error are monitored, the amplitude offset rate, frequency error, and phase angle change of the data nodes are calculated, and the data nodes that exceed the standard range are screened to obtain the abnormal data node set;

[0057] For the historical operation data of a specific monitoring point, the initial voltage amplitude, frequency and phase angle data are obtained. The initial data of a substation are: voltage amplitude 230V, frequency 50.05Hz, phase angle error 0.5°. High-precision sensors are used for data collection, and continuous monitoring is performed at intervals of 1s. The monitoring time is set to 10 minutes, and the number of data points is 600. After data collection at each time point, the amplitude offset rate, frequency error and phase angle change of each data node are calculated. The calculation method is as follows: amplitude offset rate calculate: ,in, Representative The voltage of each data node, Represents the system reference voltage (set to 230V). If the sampling voltage at a certain moment is 235V, the offset rate is calculated as follows: , similarly, the frequency error The calculation is as follows: ,in, Representative The frequency of data nodes, Set to 50Hz, if at a certain moment ,but , phase angle change The calculation is as follows: ,in, For the The phase angle of the data node, is the reference phase angle (set to 0°), if at a certain moment ,but: If the amplitude deviation rate of a data point exceeds 5%, the frequency error exceeds 0.2 Hz, and the phase angle change exceeds 1°, the data point is marked as an abnormal data point and recorded as an abnormal data node set.

[0058] S112: Call the abnormal data node set, use the data backtracking mechanism to restore the missing data information from the backup system, perform hash value comparison, filter out the data nodes with mismatched hash values, and obtain the data integrity abnormal point set;

[0059] Use the data backtracking mechanism to retrieve lost or abnormal data within 10 minutes from the backup system. Assume that the backtracking mechanism recovers data at a certain abnormal time from the backup database: voltage 229V, frequency 50Hz, phase angle 0.3°. Perform hash value calculation on the recovered data. The calculation method is as follows: ,After calculating the hash value, it is compared with the standard hash value stored in the ,system. If the hash value does not match, it is considered that the data integrity ,is abnormal, and the data point is recorded in the data integrity ,abnormal node set.

[0060] S113: Call the data integrity abnormal point set, remove abnormal data nodes, and evaluate the voltage amplitude, frequency offset and phase angle error using the formula: ;

[0061] Calculate data quality assessment values , and screen qualified data nodes according to the evaluation value to obtain the power data processing results, among which, Representative The voltage amplitude of each data node, represents the voltage reference value, Representative The frequency of data nodes, represents the frequency reference value, Representative The phase angle of the data node, represents the phase angle reference value, Represents the total number of data nodes, represents the standard deviation of the voltage data, represents the standard deviation of frequency data, represents the standard deviation of the phase angle data;

[0062] Remove abnormal data nodes, screen the remaining data nodes, calculate the voltage amplitude, frequency offset and phase angle error of each node, and build a data quality assessment model based on the calculated data. , set the standard deviation , , , take some data examples as shown in the following table:

[0063] Power data monitoring point data table

[0064]

[0065] As shown in the table above, calculate When , take 4 data points as an example:

[0066] ;

[0067] ;

[0068] If the quality interval is 0.8≤ If the value is ≤1.2, the result is in line with the interval, which means that the overall deviation of the screened data nodes is small and the data integrity and accuracy meet the standards. Therefore, the data nodes can be used for subsequent power system analysis, scheduling and monitoring without further data supplementation or correction.

[0069] See also Figure 3 ,The specific steps for obtaining the power feature balancing configuration are:

[0070] S211: Based on the power data processing results, collect power load characteristics, equipment operating parameters, and time series data, extract the load power, equipment current, and voltage change trends of each data point, and analyze the distribution of characteristics in the time dimension to obtain the power characteristic time series distribution;

[0071] During the data collection phase, it is necessary to monitor the operating status of different power systems and record their key operating parameters at different time points, such as the voltage, current, frequency of the substation and the power consumption of the load equipment. Assuming that the daily power load of the load equipment of a substation fluctuates periodically, the load is higher during the morning peak (7:00-9:00) and evening peak (18:00-21:00) periods, and the load is lowest at night (23:00-5:00), then during the data extraction process, it is necessary to record the power, equipment current and voltage data of the key time periods separately, and calculate their changing trends at different time points. First, calculate the load power :

[0072] ;

[0073] in, is the voltage, is the current, is the power factor. At a certain moment, the voltage is 230V, the current is 50A, and the power factor is 0.85. Then:

[0074] Similarly, calculate the rate of change of device current: ;

[0075] in, is the current value at the current time point, is the current value at the previous time point. If the current increases from 40A to 50A at 8:00, then: ;

[0076] If the value exceeds a certain threshold (for example, 20%), it is considered that the load at that time point has changed significantly. In addition, the voltage change trend can be calculated by sliding average:

[0077] If at some point ,but: ;

[0078] By calculating and comparing the load power, equipment current, and voltage change trends at different time points, we can obtain their distribution in the time dimension and the time series distribution of power characteristics.

[0079] S212: Based on the time series distribution of power features, calculate the correlation coefficient between each feature, screen the key features of mutual dependence, and analyze their correlation with the power system operation state to obtain the power key feature set;

[0080] During the operation of the power system, there are interdependencies between multiple characteristic variables. For example, power load, equipment current, voltage fluctuations, etc. will affect the stability of the system. In order to screen out key features with strong interdependence, it is necessary to statistically analyze the changes in each characteristic data at different time points and calculate the correlation coefficient between each feature. First, obtain the characteristic data at different time points and calculate its mean and standard deviation. For example, the load power recorded by a substation at different time points and device current as follows:

[0081] 7:00 Load power 5000W, equipment current 22A;

[0082] 12:00 Load power 5500W, equipment current 24A;

[0083] 18:00 Load power 6000W, equipment current 27A;

[0084] 21:00 Load power 6200W, equipment current 28A;

[0085] It can be seen that the device current and load power show a trend of synchronous change, so it is necessary to calculate the correlation between the two to determine whether there is a strong dependence. The correlation calculation is based on the covariance and standard deviation of the feature variables. For example, if the correlation coefficient between the device current and load power is close to 1, it indicates that there is a high correlation between the two. If it is close to 0, it means that there is almost no correlation. When screening features, a correlation threshold is usually set, such as 0.3. If the correlation coefficient of a feature with other features is lower than 0.3, it is considered that it has little impact on the system operation status and is not retained as a key feature. If the correlation coefficient of a feature is higher than 0.8, it indicates that it has a strong dependence on other key features and can be included in the key feature set. In addition, in addition to calculating the numerical correlation between features, it is also necessary to analyze their actual significance in the operation of the power system. For example, if it is found that the load power and the device current are highly correlated, the current change can be directly used to predict the load fluctuation, thereby reducing unnecessary data redundancy and obtaining the power key feature set.

[0086] S213: Call the power key feature set, reformat the feature representation, and use the formula based on the standardized mean and feature deviation: ;

[0087] Calculating feature balance , and adjust the feature normalization parameters to obtain the power feature balancing configuration, where Representative Power characteristic values, Representative characteristics The mean of Representative characteristics The standard deviation of Represents the total number of feature data points;

[0088] For the selected key feature set, feature balancing is required so that different features have the same scale after normalization. The key feature of a power system is power and current , some sample data are shown in the following table:

[0089] Key Characteristics Data Table

[0090]

[0091] Calculate the mean based on the data in the above table: ;

[0092] ;

[0093] Then calculate the standard deviation: ;

[0094] ;

[0095] ;

[0096] ;

[0097] ;

[0098] ;

[0099] Next, calculate the feature balance :

[0100] ;

[0101] ;

[0102] ;

[0103] Similarly, calculate the current balance: ;

[0104] ;

[0105] ;

[0106] The obtained balance The balance degree is 0.93 (power) and 0.90 (current), and the qualified range is 0.85≤ ≤1.15, which means that the selected key features have good balance after normalization, and the differences between different features in the data scale are small. Therefore, they can be directly used for further analysis and scheduling of the power system to obtain a balanced configuration of power features.

[0107] See also Figure 4 ,The specific steps for obtaining the dynamic indicators of electricity growth trend are as follows:

[0108] S311: Based on the power feature balancing configuration, analyze the power load curve, calculate the power change rate within the difference time window, continuously detect the power change value, and calculate the average power change rate at each time interval to generate power change data;

[0109] Call the historical power load curve data, select the load power value in the past cycle, and combine it with the real-time power measurement data to divide the data set into time windows. The length of each time window can be set according to the actual situation, such as 5 minutes or 0 minutes as a unit. Extract the power values of all sampling points in the time window and calculate its change rate. In the calculation process, the power change calculation formula is used: ,in, Represents the power change rate at the current moment, is the power value at the current moment, is the power value at the previous moment, The time interval between two time points. In the continuous change process of the power load curve, this formula is used to characterize the change trend of the load power over time. Subsequently, the calculated power change rate data is subjected to continuity detection, that is, to determine whether its change trend in multiple consecutive time windows is stable, and to set the power change rate threshold. , when the power change rate Multiple consecutive time windows exceeded When , mark this time period as a period of drastic change, and focus on the data changes in this interval in the next calculation. At the same time, calculate the average change rate of the power value in each time window. The formula is as follows: ,in, Represents the average power change rate within a certain period of time, is the instantaneous power change rate in each time window, is the total number of time windows. After obtaining the average change rate of all time windows, a power change data set is formed to generate power change data.

[0110] S312: Calculate the rate increment value based on the power change data, set a dynamic screening threshold, screen the time intervals where the rate increment exceeds the threshold, and obtain a set of power demand growth intervals;

[0111] First, based on the generated power change data set, the average change rate of each time window is extracted and the rate increment is calculated. The rate increment is calculated as follows: ,in, Represents the rate increment value, and Represents the average power change rate of two adjacent time windows. Exceeds the set rate increment threshold When the power demand increases significantly in the time window, the threshold It can be obtained based on historical data statistics. For example, it can be set as the mean of all rate increments in the past cycle plus the standard deviation, that is: ,in, represents the mean value of the rate increment of all time windows, Represents the standard deviation of the rate increment value. This method can adaptively adjust the screening threshold to filter out the time window where the rate increment exceeds the threshold and mark it as the interval of rapid growth of power demand, thereby obtaining the power demand growth interval set.

[0112] S313: Call the power demand growth interval set, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, match the current power usage trend, and use the formula:

[0113] ;

[0114] Get dynamic indicators of electricity growth trends ,in, Represents the change in power input data, Represents the total number of power data points in the time interval, represents the weight coefficient of the power input data, Represents the fluctuation offset of the power load curve within the target time interval, represents the total number of data points in the fluctuation analysis, An adjustment factor representing the shift trend;

[0115] If the change in power input data within a certain period of time is kW, total number of data points , the fluctuation offset of the power load curve is kW, total number of data points , set the weight of power input data , offset trend adjustment factor , substitute into the calculation: ;

[0116] ;

[0117] The results show that the dynamic index of electricity growth trend is 6.2, which represents the comprehensive situation of the current electricity demand growth trend. If the value exceeds a preset range, for example, higher than 6.0, it can be determined that the electricity demand has increased significantly, and adjustment strategies should be adopted to optimize power dispatch.

[0118] See also Figure 5 ,The specific steps for obtaining supply and demand balance assessment data are as follows:

[0119] S411: Based on the dynamic indicators of power growth trends, analyze the load parameters of the transmission lines, normalize the power transfer ratio of each group of transmission lines, and obtain the transmission line load ratio;

[0120] First, obtain the rated power and actual transmission power data of the transmission line. For example, the rated power of a transmission line is 500MW and the actual transmission power is 350MW. Calculate the load parameter of the line, that is, the load factor. The calculation formula is: Load factor = (actual transmission power / rated power) × 100%. Substituting the data into this formula, we get: Load factor = (350MW / 500MW) × 100% = 70%, indicating that the line is operating at 70% of its maximum capacity. Next, normalize the power transfer ratio of each group of transmission lines. Suppose there are three transmission lines with actual transmission powers of 350MW, 275MW, and 400MW, respectively. First, calculate the total transmission power: 350MW + 275MW + 400MW = 1025MW. Then, calculate the power transfer ratio of each line:

[0121] Line 1: 350MW / 1025MW≈0.341;

[0122] Line 2: 275MW / 1025MW≈0.268;

[0123] Line 3: 400MW / 1025MW≈0.390;

[0124] Finally, the ratios are normalized so that their sum is 1. The normalized power transfer ratio is:

[0125] Line 1: 0.341 / (0.341+0.268+0.390)≈0.341

[0126] Line 2: 0.268 / (0.341+0.268+0.390)≈0.268

[0127] Line 3: 0.390 / (0.341+0.268+0.390)≈0.390

[0128] The normalized power transfer ratio reflects the relative contribution of each line to the total transmission power. Finally, the transmission line load ratio is obtained to evaluate the load condition of each line.

[0129] S412: Calculate the supply-demand deviation value of each grid zone based on the transmission line load ratio and the grid zone power supply capacity parameter, and determine the current power supply status to obtain the grid zone supply-demand deviation value;

[0130] Based on the transmission line load ratios calculated above and combined with the power supply capacity parameters of the grid sections, the supply and demand balance in each section is evaluated. Assume that the grid is divided into three sections, A, B, and C, with power supply capacities of 50 MW, 60 MW, and 70 MW, respectively. Through real-time monitoring, the actual load demands of each section are 45 MW, 65 MW, and 68 MW, respectively. The supply-demand deviation for each section is calculated as: power supply capacity minus actual load demand. Therefore, the supply-demand deviation for Section A is 5 MW (50 MW - 45 MW), for Section B it is -5 MW (60 MW - 65 MW), and for Section C it is 2 MW (70 MW - 68 MW). The current power supply status is determined based on the supply-demand deviation: a positive deviation indicates a surplus power supply; a negative deviation indicates a shortage. Therefore, Sections A and C have a surplus power supply, while Section B has a shortage power supply. This analysis provides the supply-demand deviation for each grid section.

[0131] S413: Based on the supply and demand deviation of the power grid zone, determine the supply and demand forecast error and optimize the analysis parameters using the formula: ;

[0132] Calculate the supply and demand balance error value , and compare the adjusted forecast data with the current data to obtain the supply and demand balance assessment data, among which, Representative The actual load demand of each grid zone, Representative The power supply capacity of each grid section, represents the total number of grid partitions;

[0133] Determine the supply and demand forecast error, which is the difference between the actual load demand and the forecast. Assuming the load demand forecasts for zones A, B, and C are 48 MW, 63 MW, and 69 MW, respectively, the forecast errors are -3 MW (45 MW - 48 MW), 2 MW (65 MW - 63 MW), and -1 MW (68 MW - 69 MW). Substituting these values into the formula:

[0134] ;

[0135] Calculated supply and demand balance error value ,The result shows that the overall supply and demand of the current ,power grid is basically balanced with a small error.,By comparing the adjusted forecast data with the current ,actual data, we obtain the supply and demand balance evaluation data, ,which provides a reference for power grid scheduling and ,planning.

[0136] See also Figure 6 ,The specific steps to obtain the power analysis deployment-ready model are:

[0137] S511: Calling supply and demand balance assessment data, assessing the power demand level, obtaining the power generation capacity of the power generation unit, and analyzing its matching degree with the demand level to obtain the power supply and demand matching degree;

[0138] Obtain real-time load data of the power grid and combine it with power forecast data to determine the power demand level in multiple time periods in the future. On this basis, collect the power generation capacity parameters of each power generation unit, analyze its maximum and minimum power output ranges, evaluate their respective regulation rates, calculate the available power of each power generation unit under different load levels, and for different time points, calculate the difference between power demand and available power generation to obtain the power profit and loss value at each moment. Set the supply and demand matching judgment threshold. Assume that the threshold is ±5%. If the power profit and loss value is within this range, it is considered that the supply and demand matching is reasonable. If it exceeds the threshold, the output power of the power generation unit that needs to be adjusted is calculated based on the excess part. Use uniform regulation or give priority to calling low-cost power generation units for supplementary calculations to adjust the load distribution of each power generation unit. Finally, calculate the supply and demand matching degree. The matching degree can be calculated by the ratio of the supply and demand difference to the demand value. For example, at a certain time point, the demand is 100MW and the power generation capacity is 95MW, then the supply and demand matching degree is , indicating that supply and demand are basically matched. If it is 110MW, the matching degree is , if it exceeds the threshold range, it is necessary to adjust the distributed load to obtain the matching degree of power supply and demand.

[0139] S512: Based on the power supply and demand matching degree and combined with the power generation cost data of the power generation units, the unit power generation cost is calculated, and the power generation unit with the optimal power generation cost is selected using the formula: ;

[0140] Calculating unit efficiency coefficient ,in, Representative The power generation of each power generation unit, Representative The power generation cost of each power generation unit, Representative The power demand in each time period, Represents the total number of all time periods;

[0141] First, obtain the fuel consumption rate of each power generation unit and calculate the unit power generation cost based on the unit fuel price. For example, if the fuel consumption rate of a coal-fired power generation unit is 0.3t / MWh and the unit fuel price is 500 yuan / t, the unit power generation cost is Yuan / MWh, and calculate the unit cost of all power generation units at the same time, set the cost threshold to 200 yuan / MWh, screen the power generation units with costs lower than the threshold and that meet the supply and demand matching, and further calculate their unit efficiency parameters using the formula:

[0142]

[0143] The data for a coal-fired power generation unit is as follows: power output: 80MW, 90MW, 100MW (corresponding to three time periods); unit power generation cost: 120 yuan / MWh, 110 yuan / MWh, 105 yuan / MWh; power demand: 100MW, 100MW, 100MW - total number of time periods: 3. Substituting this data into the formula:

[0144] ;

[0145] ;

[0146] ;

[0147] Comparative results show that coal-fired power generation units , gas-fired power generation units Therefore, the unit efficiency coefficient of the coal-fired power generation unit is better, and it is selected into the power generation unit list to obtain the unit efficiency coefficient.

[0148] S513: Based on the unit efficiency coefficient, combined with the selected power generation units, and according to the real-time load and power forecast data of the power grid, an executable model file is created to obtain a power analysis deployment-ready model;

[0149] Obtain the power output range of the selected optimal power generation unit, calculate its power adjustment range under different load conditions, set the load adjustment cycle, for example, adjust the power distribution every 15 minutes, obtain the current load level based on real-time load data, and calculate the load trend for the next adjustment cycle based on forecast data. For example, if the current load is 200MW and the load is predicted to increase to 210MW in 10 minutes, calculate the required increased power generation and perform power scheduling based on the power generation unit with the optimal unit efficiency coefficient to ensure that the power distribution is within the adjustable range. Generate an executable model file containing load adjustment plans for all time periods to obtain a power analysis deployment-ready model.

[0150] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for rapidly constructing a power data analysis model based on big data, characterized in that: The following steps are involved: S1: Based on the substation voltage, current, and power data, the voltage amplitude, frequency offset, and phase angle error are monitored to check data integrity, remove abnormal data node information, and obtain power data processing results; S2: Based on the power data processing results, collect power load characteristics, equipment operating parameters and time series data, evaluate the interdependence between each characteristic, screen key characteristics of the power system, and obtain a balanced configuration of power characteristics; The steps for obtaining the power feature balancing configuration are specifically as follows: S211: Based on the power data processing results, collect power load characteristics, equipment operating parameters and time series data, extract the load power, equipment current and voltage change trends of each data point, and analyze the distribution of characteristics in the time dimension to obtain the power characteristic time series distribution; S212: Based on the power feature time series distribution, calculate the correlation coefficient between each feature, screen the key features of mutual dependence, and analyze their correlation with the power system operation state to obtain the key features of the power system; S213: Call the key features of the power system, reformat the feature representation, and use the formula based on the standardized mean and feature deviation: ; Calculating feature balance , and adjust the feature normalization parameters to obtain the power feature balancing configuration, where Representative Power characteristic values, Representative characteristics The mean of Representative characteristics The standard deviation of Represents the total number of feature data points; S3: Based on the power characteristic balancing configuration, calculate the power change rate within the difference time window, select the time interval of power demand growth, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, and obtain the power growth trend dynamic indicator; S4: Analyze the load parameters of the transmission lines and the power supply status of the power grid zones based on the power growth trend dynamic indicators, determine the power supply and demand status of each zone, and obtain supply and demand balance assessment data; S5: Calling the supply and demand balance assessment data, analyzing and selecting the most efficient power generation unit, and then combining it with the real-time load and power forecast data of the power grid to obtain a power analysis deployment-ready model; The steps for obtaining the power analysis deployment-ready model are as follows: S511: Calling the supply and demand balance assessment data, assessing the power demand level, obtaining the power generation capacity of the power generation unit, and analyzing the degree of matching between the power generation capacity and the demand level to obtain the power supply and demand matching degree; S512: Based on the power supply and demand matching degree and combined with the power generation cost data of the power generation units, the unit power generation cost is calculated, and the power generation unit with the best power generation cost is selected using the formula: ; Calculating unit efficiency coefficient ,in, Representative The power generation of each power generation unit, Representative The power generation cost of each power generation unit, Representative The power demand in each time period, Represents the total number of all time periods; S513: Based on the unit efficiency coefficient, combined with the screened power generation units, and according to the real-time load and power forecast data of the power grid, an executable model file is created to obtain a power analysis deployment-ready model.

2. The method for rapidly constructing a power data analysis model based on big data according to claim 1, characterized in that: The power data processing results include data integrity records and abnormal node indexes; the power growth trend dynamic indicators include rate change analysis results, growth interval identification results, and data weights; the supply and demand balance assessment data specifically include load status information, prediction error assessment results, and analysis parameter details; the power analysis deployment-ready model includes power generation efficiency data, cost-effectiveness data, and load response configuration.

3. The method for rapidly constructing a power data analysis model based on big data according to claim 1, characterized in that: The steps for obtaining the power data processing results are specifically as follows: S111: Based on the voltage, current, and power data of the substation, the voltage amplitude, frequency offset, and phase angle error are monitored, the amplitude offset rate, frequency error, and phase angle change of the data nodes are calculated, and the data nodes that exceed the standard range are screened to obtain the abnormal data node set; S112: Calling the abnormal data node set, using the data backtracking mechanism to restore missing data information from the backup system, performing hash value comparison, screening data nodes with unmatched hash values, and obtaining a data integrity abnormal point set; S113: Call the data integrity abnormal point set, remove abnormal data nodes, evaluate voltage amplitude, frequency offset and phase angle error, and use the formula: ; Calculate data quality assessment values , and screen qualified data nodes according to the evaluation value to obtain the power data processing results, among which, Representative The voltage amplitude of each data node, represents the voltage reference value, Representative The frequency of data nodes, represents the frequency reference value, Representative The phase angle of the data node, represents the phase angle reference value, Represents the total number of data nodes, represents the standard deviation of the voltage data, represents the standard deviation of frequency data, Represents the standard deviation of the phase angle data.

4. The method for rapidly constructing a power data analysis model based on big data according to claim 1, characterized in that: The steps for obtaining the power growth trend dynamic indicator are specifically as follows: S311: Based on the power feature balancing configuration, analyze the power load curve, calculate the power change rate within the difference time window, continuously detect the power change value, and calculate the average power change rate at each time interval to generate power change data; S312: Calculating a rate increment value based on the power change data, setting a dynamic screening threshold, screening time intervals where the rate increment exceeds the threshold, and obtaining a set of power demand growth intervals; S313: Call the power demand growth interval set, analyze the fluctuation offset of the target time interval, adjust the weight of the power input data, match the current power usage trend, and use the formula: ; Get dynamic indicators of electricity growth trends ,in, Represents the change in power input data, Represents the total number of power data points in the time interval, represents the weight coefficient of the power input data, Represents the fluctuation offset of the power load curve within the target time interval, represents the total number of data points in the fluctuation analysis, An adjustment factor representing the shift in trend.

5. The method for rapidly constructing a power data analysis model based on big data according to claim 1, characterized in that: The steps for obtaining the supply and demand balance assessment data are specifically as follows: S411: Analyze transmission line load parameters based on the power growth trend dynamic indicator, normalize the power transfer ratio of each group of transmission lines, and obtain a transmission line load ratio; S412: Calculating the supply-demand deviation value of each power grid zone based on the transmission line load ratio and the power supply capacity parameter of the power grid zone, and determining the current power supply status to obtain the power grid zone supply-demand deviation value; S413: Based on the power grid partition supply and demand deviation, determine the supply and demand forecast error, optimize the analysis parameters, and use the formula: ; Calculate the supply and demand balance error value , and compare the adjusted forecast data with the current data to obtain the supply and demand balance assessment data, among which, Representative The actual load demand of each grid zone, Representative The power supply capacity of each grid segment, Represents the total number of grid partitions.

Images