CN120196904B - Rapid construction method of electric power data analysis model based on big data - Google Patents
Rapid construction method of electric power data analysis model based on big dataInfo
- Publication number
- CN120196904B CN120196904B CN202510670075.9A CN202510670075A CN120196904B CN 120196904 B CN120196904 B CN 120196904B CN 202510670075 A CN202510670075 A CN 202510670075A CN 120196904 B CN120196904 B CN 120196904B
- Authority
- CN
- China
- Prior art keywords
- power
- data
- demand
- load
- supply
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of model construction, in particular to a rapid construction method of an electric power data analysis model based on big data, which comprises the following steps: based on voltage, current and power data of the transformer substation, monitoring voltage amplitude, frequency offset and phase angle error, detecting data integrity, removing abnormal data node information, and obtaining a power data processing result. According to the invention, the prediction precision of the power demand is optimized by enhancing the verification of the data integrity and the accurate extraction of the key features, the reliability of the data is ensured by combining the pairs of data backtracking and Ha Xibi, the quality of data input is improved by deeply analyzing the power load features and the equipment operation parameters, the analysis of the power system behavior is optimized, the weight of the power input data is dynamically adjusted to match the actual use trend, and the application flexibility and the real-time response capability of a data analysis model are enhanced, so that the aspects of resource allocation and power generation efficiency are optimized.
Description
Technical Field
The invention relates to the technical field of model construction, in particular to a rapid construction method of an electric power data analysis model based on big data.
Background
Model construction, which is a core component in the fields of data science, artificial intelligence, machine learning, etc., is particularly focused on how to use the collected large amount of power usage data to predict power demand, optimize power generation and distribution resources, and improve the energy efficiency and reliability of the system, refers to creating a mathematical or simulation model to simulate real world processes, systems or phenomena, mainly for prediction, optimization, and decision support.
The rapid construction method of the large-data power data analysis model aims at rapidly developing a model capable of processing and analyzing a large-scale power data set so as to utilize the power data to conduct deep research on energy use of rural enterprises, is particularly focused on collecting power use data of the enterprises in a specific time period so as to calculate power generation values, is beneficial to providing necessary data support for energy conservation transformation of high-energy consumption equipment and providing intelligent diagnosis service of the power equipment for high-voltage enterprise customers, and in addition, the model also supports real-time energy consumption analysis, accurately monitors safe production conditions of a production area, establishes a power consumption tracking account, is specially used for monitoring power load of agricultural product enterprises and timely assists in meeting power requirements in production.
The prior art has the defects in terms of data integrity verification and dynamic adjustment mechanisms, the accuracy of power demand prediction and the efficiency of resource allocation are limited, the defects of the effective data verification mechanisms cause that data errors are difficult to discover and correct in time, the accuracy of power data analysis is affected, in addition, the existing method has insufficient potential in terms of model optimization by utilizing power load characteristics and equipment operation parameters, the power demand cannot be accurately predicted in the period of peak demand, the power resource allocation is uneven due to insufficient prediction, and the production efficiency and the stability of a power system are affected.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a rapid construction method of an electric power data analysis model based on big data.
In order to achieve the purpose, the invention adopts the following technical scheme that the rapid construction method of the electric power data analysis model based on big data comprises the following steps:
S1, monitoring voltage amplitude, frequency offset and phase angle error based on voltage, current and power data of a transformer substation, detecting data integrity, removing abnormal data node information, and obtaining a power data processing result;
s2, collecting power load characteristics, equipment operation parameters and time sequence data according to the power data processing result, evaluating the interdependence among each characteristic, screening key characteristics of a power system, and obtaining power characteristic balanced configuration;
S3, calculating the power change rate in a difference time window based on the power feature balance configuration, screening a time interval in which the power demand is increased, analyzing the fluctuation offset of a target time interval, and adjusting the weight of power input data to obtain a dynamic index of the power increase trend;
s4, analyzing the load parameters of the power transmission line and the power supply conditions of the power grid subareas according to the dynamic indexes of the power growth trend, judging the power supply and demand state of each subarea, and obtaining supply and demand balance evaluation data;
and S5, calling the supply and demand balance evaluation data, analyzing and screening the power generation unit with optimal efficiency, and acquiring a power analysis deployment ready model by combining the real-time load and power prediction data of the power grid.
The invention improves the power data processing results, wherein the power data processing results comprise data integrity records and abnormal node indexes, the power characteristic balance configuration comprises a load characteristic set, a device parameter set and a time sequence set, the power growth trend dynamic index comprises a rate change analysis result, a growth interval identification result and a data weight condition, the supply and demand balance evaluation data comprises load state information, a prediction error evaluation result and analysis parameter details, and the power analysis deployment ready model comprises power generation efficiency data, cost benefit data and load response configuration.
The invention improves that the step of obtaining the electric power data processing result comprises the following steps:
s111, based on voltage, current and power data of a transformer substation, monitoring voltage amplitude, frequency offset and phase angle error, calculating amplitude offset, frequency error amount and phase angle variation amount of data nodes, screening data nodes beyond a standard range, and obtaining an abnormal data node set;
S112, invoking the abnormal data node set, recovering missing data information from the backup system by utilizing a data backtracking mechanism, performing hash value comparison, screening data nodes with unmatched hash values, and obtaining a data integrity abnormal node set;
s113, calling the data integrity abnormal point set, removing abnormal data nodes, evaluating voltage amplitude, frequency offset and phase angle error, and adopting the formula: ;
calculating data quality evaluation value And screening qualified data nodes according to the evaluation value to obtain a power data processing result, wherein,Represents the firstThe voltage amplitude of the individual data nodes,Representing the value of the voltage reference and,Represents the firstThe frequency of the individual data nodes is determined,Represents the reference value of the frequency and,Represents the firstThe phase angle of the individual data nodes is,Representing the phase angle reference value,Representing the total number of data nodes,Representing the standard deviation of the voltage data,Representing the standard deviation of the frequency data,Representing the standard deviation of the phase angle data.
The invention improves that the acquisition steps of the electric power characteristic balance configuration specifically comprise:
s211, collecting power load characteristics, equipment operation parameters and time sequence data according to the power data processing result, extracting the load power, equipment current and voltage change trend of each data point, analyzing the distribution condition of the characteristics in the time dimension, and obtaining power characteristic time sequence distribution;
S212, calculating a correlation coefficient between each feature based on the power feature time sequence distribution, screening features with critical interdependence, analyzing the correlation between the features and the running state of the power system, and obtaining a power key feature set;
s213, calling the power key feature set, reformatting the feature representation, and adopting the formula according to the standardized mean value and the feature deviation: ;
calculating feature equality And adjusting the characteristic normalization parameters to obtain the power characteristic balance configuration, wherein,Represents the firstThe characteristic value of the electric power is calculated,Representative characteristicsIs used for the average value of (a),Representative characteristicsIs set in the standard deviation of (a),Representing the total number of characteristic data points.
The invention improves that the step of obtaining the dynamic index of the power growth trend is as follows:
S311, analyzing a power load curve based on the power characteristic balanced configuration, calculating a power change rate in a difference time window, continuously detecting a power change value, calculating an average change rate of power at time intervals, and generating power change data;
S312, calculating a rate increment value based on the power change data, setting a dynamic screening threshold value, and screening a time interval in which the rate increment exceeds the threshold value to obtain a power demand increase interval set;
S313, calling the power demand increase interval set, analyzing the fluctuation offset of the target time interval, adjusting the weight of the power input data, matching the current power use trend, and adopting the formula: ;
obtaining dynamic index of power growth trend , wherein,Representing the amount of change in the power input data,Representing the total number of power data points in the time interval,A weight coefficient representing the power input data,Representing the fluctuating offset of the power load curve over the target time interval,Representing the total number of data points in the fluctuation analysis,An adjustment factor representing the tendency of the shift.
The invention improves that the acquisition steps of the supply and demand balance evaluation data specifically comprise:
s411, analyzing power transmission line load parameters based on the dynamic indexes of the power growth trend, normalizing the power transmission ratio of each group of power transmission lines, and obtaining the power transmission line load ratio;
s412, calculating the supply and demand deviation value of each subarea based on the load ratio of the power transmission line and combining the subarea power supply capacity parameter of the power grid, and judging the current power supply state to obtain the subarea supply and demand deviation value of the power grid;
S413, determining a supply and demand prediction error, optimizing analysis parameters and adopting a formula based on the supply and demand deviation of the power grid partition: ;
Calculating a supply and demand balance error value And comparing the adjusted predicted data with the current data to obtain supply-demand balance evaluation data, wherein,Represents the firstThe actual load demands of the individual grid partitions,Represents the firstThe power supply capacity of the individual grid partitions,Representing the total number of grid partitions.
The invention improves that the acquisition steps of the electric power analysis deployment ready model are as follows:
s511, calling the supply and demand balance evaluation data, evaluating the power demand level, acquiring the power generation capacity of the power generation unit, and analyzing the matching degree between the power generation unit and the demand level to obtain the power supply and demand matching degree;
S512, calculating unit power generation cost based on the power supply and demand matching degree and combining the power generation cost data of the power generation units, screening the power generation unit with the optimal power generation cost, and adopting the formula: ;
Calculating a coefficient of unit efficiency , wherein,Represents the firstThe power generated by the power generation units,Represents the firstThe power generation cost of the individual power generation units,Represents the firstThe power requirements of the individual time periods,Representing the total number of all time periods;
and S513, based on the unit efficiency coefficient, combining the screened power generation units, creating an executable model file according to the real-time load and the power prediction data of the power grid, and obtaining a power analysis deployment ready model.
Compared with the prior art, the invention has the advantages and positive effects that:
According to the invention, the prediction precision of the power demand is optimized by enhancing the verification of the data integrity and the accurate extraction of key features, the reliability of the data is ensured by combining the backtracking and Ha Xibi pairs of data, the quality of data input is improved by deeply analyzing the power load features and the equipment operation parameters, the analysis of the power system behavior is optimized, the application flexibility and the real-time response capability of a data analysis model are enhanced by dynamically adjusting the weight of the power input data to match the actual use trend, and therefore, the utilization efficiency of the power resource is improved, and the energy safety and the energy efficiency of the power production are ensured.
Drawings
FIG. 1 is a flow chart of a method for quickly constructing an electric power data analysis model based on big data;
FIG. 2 is a flowchart of the power data processing result acquisition in the present invention;
FIG. 3 is a flow chart of the power feature balancing configuration acquisition in the present invention;
FIG. 4 is a flow chart of the power growth trend dynamic index acquisition in the present invention;
FIG. 5 is a flow chart of the acquisition of the supply and demand balance evaluation data according to the present invention;
FIG. 6 is a flow chart of the acquisition of the power analysis deployment-ready model in the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," etc. indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the invention and simplify description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Examples
Referring to fig. 1, the invention provides a method for quickly constructing an electric power data analysis model based on big data, which comprises the following steps:
s1, monitoring voltage amplitude, frequency offset and phase angle error based on voltage, current and power data of a transformer substation, recovering missing data information from a backup system by utilizing a data backtracking mechanism, performing hash value comparison, detecting data integrity, removing abnormal data node information and obtaining a power data processing result;
S2, collecting power load characteristics, equipment operation parameters and time sequence data according to a power data processing result, evaluating the interdependence among the characteristics, screening key characteristics of a power system, reformatting characteristic representations, and obtaining power characteristic balanced configuration;
S3, analyzing a power load curve based on power characteristic balanced configuration, calculating a power change rate in a difference time window, screening a time interval in which power demand is increased, analyzing fluctuation offset of a target time interval, adjusting weight of power input data, and matching a current power use trend to obtain a power increase trend dynamic index;
S4, analyzing load parameters of the power transmission line and power supply conditions of the power grid subareas according to dynamic indexes of the power growth trend, judging power supply and demand states of each subarea, determining supply and demand prediction errors, optimizing analysis parameters, and comparing the adjusted prediction data with current data to obtain supply and demand balance evaluation data;
and S5, invoking supply and demand balance evaluation data, collecting available power generation parameters and power generation cost data, analyzing and screening power generation units (power plants or power generator sets) with optimal efficiency, and creating an executable model file by combining real-time load and power prediction data of a power grid to obtain a power analysis deployment ready model.
The power data processing result comprises a data integrity record and an abnormal node index, the power characteristic balance configuration is specifically a load characteristic set, a device parameter set and a time sequence set, the power growth trend dynamic index comprises a rate change analysis result, a growth interval identification result and a data weight condition, the supply-demand balance evaluation data is specifically load state information, a prediction error evaluation result and analysis parameter details, and the power analysis deployment ready model comprises power generation efficiency data, cost benefit data and load response configuration.
Referring to fig. 2, the steps for obtaining the power data processing result specifically include:
s111, based on voltage, current and power data of a transformer substation, monitoring voltage amplitude, frequency offset and phase angle error, calculating amplitude offset, frequency error amount and phase angle variation amount of data nodes, screening data nodes beyond a standard range, and obtaining an abnormal data node set;
For historical operation data of specific monitoring points, initial voltage amplitude, frequency and phase angle data are acquired, wherein the initial data of a certain transformer substation are voltage amplitude 230V, frequency 50.05Hz, phase angle error 0.5 DEG, data acquisition is carried out by adopting a high-precision sensor, continuous monitoring is carried out at time intervals of 1s, the monitoring time is set to be 10 minutes, the number of data points is 600, after data acquisition of each time point, the amplitude deviation rate, the frequency error amount and the phase angle change amount of each data node are calculated, and the calculation mode is as follows And (3) calculating: , wherein, Represents the firstThe voltage at the data node of the data node,Representative system reference voltage (set to 230V), if the sampling voltage at a certain time is 235V, the offset rate is calculated as follows: Similarly, the frequency error amount The calculation is as follows: , wherein, Represents the firstThe frequency of the individual data nodes is determined,Set to 50Hz, if at a certain momentThenPhase angle variationThe calculation is as follows: , wherein, Is the firstThe phase angle of the individual data nodes is,For reference phase angle (set to 0 °), if at a certain momentThen: if the amplitude deviation rate of a certain data point exceeds 5%, the frequency error amount exceeds 0.2Hz, and the phase angle change amount exceeds 1 DEG, the data point is marked as an abnormal data point, and the abnormal data point is recorded as an abnormal data node set.
S112, invoking an abnormal data node set, recovering missing data information from a backup system by utilizing a data backtracking mechanism, performing hash value comparison, screening data nodes with unmatched hash values, and obtaining a data integrity abnormal node set;
And (3) retrieving lost or abnormal data within 10 minutes from the backup system by adopting a data backtracking mechanism, wherein the data at a certain abnormal time point is recovered from the backup database by adopting the backtracking mechanism, namely, the voltage 229V, the frequency 50Hz and the phase angle 0.3 DEG, and the Hash value calculation is carried out on the recovered data by adopting the following calculation modes: after calculating the hash value, comparing the hash value with a standard hash value stored in a system, if the hash value is not matched, considering that the data integrity is abnormal, and recording the data point to a data integrity abnormal node set.
S113, calling a data integrity abnormal point set, removing abnormal data nodes, evaluating voltage amplitude, frequency offset and phase angle error, and adopting the formula:;
calculating data quality evaluation value And screening qualified data nodes according to the evaluation value to obtain a power data processing result, wherein,Represents the firstThe voltage amplitude of the individual data nodes,Representing the value of the voltage reference and,Represents the firstThe frequency of the individual data nodes is determined,Represents the reference value of the frequency and,Represents the firstThe phase angle of the individual data nodes is,Representing the phase angle reference value,Representing the total number of data nodes,Representing the standard deviation of the voltage data,Representing the standard deviation of the frequency data,Representing the standard deviation of the phase angle data;
Removing abnormal data nodes, screening the rest data nodes, calculating voltage amplitude, frequency offset and phase angle error of each node, constructing a data quality evaluation model based on calculated data, and calculating the number of data points Set standard deviation,,Examples of partial data are shown in the following table:
Power data monitoring point data table
As shown in the above table, calculateTake 4 data points as an example:
;
;
if the quality is qualified, the interval is 0.8-0 And less than or equal to 1.2, the result accords with the interval, which means that the whole deviation of the screened data nodes is smaller, and the data nodes belong to the range that the data integrity and the accuracy accord with the standard, so that the data nodes can be used for analysis, scheduling and monitoring of a subsequent power system without further data supplement or correction.
Referring to fig. 3, the step of obtaining the power feature balance configuration specifically includes:
s211, collecting power load characteristics, equipment operation parameters and time sequence data according to a power data processing result, extracting the load power, equipment current and voltage change trend of each data point, analyzing the distribution condition of the characteristics in the time dimension, and obtaining power characteristic time sequence distribution;
In the data collection stage, different power system operation states need to be monitored, key operation parameters of the power system operation states at different time points, such as voltage, current, frequency and power consumption condition of load equipment of a transformer substation, if the daily power consumption load of the load equipment of a certain transformer substation shows periodic fluctuation, the load is higher in early peak (7:00-9:00) and late peak (18:00-21:00) periods, and the load is lowest in night (23:00-5:00), the power, equipment current and voltage data of the key time periods need to be recorded respectively in the data extraction process, and the change trend of the power, the equipment current and the voltage data at different time points is calculated, and firstly, the load power is calculated :
;
Wherein, the In the form of a voltage, the voltage is,In the event of a current flow,For a power factor, the voltage at a certain time is 230V, the current is 50A, and the power factor is 0.85, then:
similarly, the rate of change of the device current is calculated: ;
wherein, the As the current value at the present point in time,For the current value at the previous time point, if at the moment 8:00, the current increases from 40A to 50A:;
if the value exceeds a certain set threshold (e.g., 20%), then the load is considered to change significantly at that point in time, and the voltage change trend can be calculated by a running average:
if at a certain moment Then:;
by calculating and comparing the variation trend of the load power, the equipment current and the voltage at different time points, the distribution condition of the load power, the equipment current and the voltage in the time dimension can be obtained, and the power characteristic time sequence distribution can be obtained.
S212, calculating a correlation coefficient between each feature based on the power feature time sequence distribution, screening features with critical interdependence, analyzing the association between the features and the running state of the power system, and obtaining a power key feature set;
In the running process of the electric power system, a plurality of characteristic variables have interdependence relations, such as electric load, equipment current, voltage fluctuation and the like, which can influence the stability of the system, in order to screen out key characteristics with strong interdependence, the change condition of each characteristic data at different time points needs to be counted, and the correlation coefficient among the characteristics is calculated, firstly, the characteristic data at different time points is obtained, and the mean value and standard deviation of the characteristic data are counted, for example, the load power recorded at different time points of a certain transformer substation And device currentThe following are provided:
7:00 load power 5000W, device current 22A;
12:00 load power 5500W, device current 24A;
18:00 load power 6000W, device current 27A;
21:00 load power 6200W, device current 28A;
it can be seen that the trend of synchronous change between the device current and the load power is presented, so that the correlation between the two needs to be calculated to determine whether a strong dependency relationship exists, the correlation calculation is calculated based on the covariance and standard deviation of the characteristic variables, for example, if the correlation coefficient between the device current and the load power is close to 1, the high correlation between the device current and the load power is indicated, if the correlation coefficient is close to 0, the correlation coefficient is almost no, a correlation threshold value, for example, 0.3, is usually set when the characteristics are screened, if the correlation coefficient between a certain characteristic and other characteristics is lower than 0.3, the influence on the running state of the system is considered to be smaller, the correlation coefficient is not reserved as a key characteristic, if the correlation coefficient between a certain characteristic is higher than 0.8, the correlation coefficient is indicated to have a strong dependency between other key characteristics, the correlation coefficient can be classified as a key characteristic set, furthermore, the actual meaning of the correlation coefficient in the running of the power system needs to be analyzed, for example, if the high correlation between the load power and the device current is found, the current change can be directly used to predict the load fluctuation, so as to reduce unnecessary data redundancy of the key characteristic set.
S213, calling a power key feature set, reformatting a feature representation, and adopting a formula according to a standardized mean value and a feature deviation:;
calculating feature equality And adjusting the characteristic normalization parameters to obtain the power characteristic balance configuration, wherein,Represents the firstThe characteristic value of the electric power is calculated,Representative characteristicsIs used for the average value of (a),Representative characteristicsIs set in the standard deviation of (a),Representing the total number of characteristic data points;
For the screened key feature set, feature equalization is needed to ensure that different features have consistent scale after normalization, and the key feature of a certain power system is power And currentPart of the sample data is as follows:
Key feature data table
Calculating the mean value according to the data in the table:;
;
The standard deviation is then calculated:
;
;
;
;
;
;
Then, feature balance is calculated :
;
;
;
And similarly, calculating the current balance degree:
;
;
;
The obtained degree of balance Is 0.93 (power) and 0.90 (current), and the equilibrium degree qualification interval is 0.85 less than or equal toThe result is less than or equal to 1.15, the screened key features have better balance after normalization, and the difference of different features on the data scale is smaller, so that the method can be directly used for further analysis and scheduling of a power system to obtain the power feature balance configuration.
Referring to fig. 4, the steps for obtaining the dynamic index of the power growth trend specifically include:
s311, analyzing a power load curve based on the power characteristic balance configuration, calculating a power change rate in a difference time window, continuously detecting a power change value, calculating an average change rate of power at time intervals, and generating power change data;
Calling historical power load curve data, selecting a load power value in a near period, combining real-time power measurement data, dividing a data set by taking a time window as a unit, setting the length of each time window according to actual conditions, for example, taking 5 minutes or 0 minutes as a unit, extracting power values of all sampling points in the time window, calculating the change rate of the power values, and adopting a power change calculation formula in the calculation process: , wherein, Representing the rate of change of power at the current time,For the power value at the current moment,For the power value at the last moment,For the time interval between two time points, in the continuous change process of the power load curve, the formula is used for representing the change trend of the load power along with time, and then, the calculated power change rate data is continuously detected, namely, whether the change trend of the calculated power change rate data in a plurality of continuous time windows is stable or not is judged, and a power change rate threshold value is setWhen the power change rateConsecutive multiple time window excessesWhen the time period is marked as a severe change time period, the data change of the interval is focused in the next calculation, and the average change rate of the power values in each time window is calculated, wherein the formula is as follows: , wherein, Representing the average rate of power change over a period of time,For the instantaneous rate of power change within each time window,And forming a power change data set to generate power change data after obtaining the average change rate of all the time windows as the total number of the time windows.
S312, calculating a rate increment value based on the power change data, setting a dynamic screening threshold value, and screening a time interval in which the rate increment exceeds the threshold value to obtain a power demand increase interval set;
Firstly, extracting the average change rate of each time window according to the generated power change data set, and calculating a rate increment value by the following calculation method: , wherein, Representing the value of the rate increment,AndRespectively representing the average power change rates of two adjacent time windows, when the rate increment valueExceeding a set rate increment thresholdWhen the power demand in the time window is judged to be obviously increased, the threshold value is determinedStatistical analysis can be performed from historical data, for example, by setting the average value of all rate increment values in the past period to be plus the standard deviation, namely: , wherein, Representing the average of the rate increment values for all time windows,The method can adaptively adjust the screening threshold value to screen out a time window in which the rate increment exceeds the threshold value, and mark a rapid power demand increase interval to obtain a power demand increase interval set.
S313, calling a power demand increase interval set, analyzing the fluctuation offset of a target time interval, adjusting the weight of power input data, matching the current power use trend, and adopting the formula:
;
obtaining dynamic index of power growth trend , wherein,Representing the amount of change in the power input data,Representing the total number of power data points in the time interval,A weight coefficient representing the power input data,Representing the fluctuating offset of the power load curve over the target time interval,Representing the total number of data points in the fluctuation analysis,An adjustment factor representing a tendency of the shift;
If the power input data change amount is within a certain period of time KW, total number of data pointsThe fluctuation offset of the power load curve isKW, total number of data pointsSetting weight of power input dataOffset trend adjustment factorSubstitution calculation:
;
;
the result shows that the dynamic index of the power increase trend is 6.2, the comprehensive situation of the current power demand increase trend is represented, if the value exceeds a certain preset interval, for example, the value is higher than 6.0, the power demand increase is judged to be remarkable, and an adjustment strategy is adopted to optimize power scheduling.
Referring to fig. 5, the acquiring steps of the supply-demand balance evaluation data specifically include:
s411, analyzing load parameters of the power transmission lines based on dynamic indexes of the power growth trend, and normalizing the power transmission ratio of each group of power transmission lines to obtain the load ratio of the power transmission lines;
Firstly, rated power and actual transmission power data of a transmission line are obtained, for example, rated power of a certain transmission line is 500MW, actual transmission power is 350MW, load parameters of the line, namely load rate are calculated, a calculation formula is that load rate= (actual transmission power/rated power) ×100%, substituted data are obtained, load rate= (350 MW/500 MW) ×100% = 70%, the transmission line is operated under 70% of the maximum capacity, next, normalization processing is carried out on power transmission ratio of each group of transmission lines, three transmission lines are assumed, actual transmission power is respectively 350MW, 275MW and 400MW, total transmission power is calculated firstly, 350MW+275MW+400MW=1025 MW, and then power transmission ratio of each line is calculated:
line 1:350MW/1025MW approximately 0.341;
Line 2:275MW/1025MW approximately 0.268;
Line 3:400MW/1025MW approximately 0.390;
finally, the ratio is normalized to make the sum of the ratio to be 1, and the normalized power transmission ratio is:
Line 1:0.341/(0.341+0.268+0.390)/(0.341)
Line 2:0.268/(0.341+0.268+0.390)/(0.268)
Line 3:0.390/(0.341+0.268+0.390)/(0.390)
The normalized power transmission ratio reflects the relative contribution of each line in the total transmission power, and finally, the load ratio of the transmission line is obtained and is used for evaluating the load condition of each line.
S412, calculating supply and demand deviation values of each subarea based on the load ratio of the power transmission line and combining the subarea power supply capacity parameters of the power grid, and judging the current power supply state to obtain the subarea supply and demand deviation values of the power grid;
Based on the calculated load ratio of the power transmission line, the supply and demand balance condition of each partition is evaluated by combining the power supply capacity parameters of the power grid partition, and the power supply capacity of the power grid is respectively 50 megawatts, 60 megawatts and 70 megawatts under the assumption that the power grid is divided into A, B, C partitions. The actual load demands of all the subareas are respectively 45 megawatts, 65 megawatts and 68 megawatts through real-time monitoring, the supply and demand deviation value = power supply capacity-actual load demand of each subarea is calculated, therefore, the supply and demand deviation of the subarea A is 5 megawatts (50 MW-45 MW), the subarea B is-5 megawatts (60 MW-65 MW), the subarea C is 2 megawatts (70 MW-68 MW), the current power supply state is judged according to the supply and demand deviation value, namely, when the deviation is positive value, the power supply surplus is represented, when the deviation is negative value, the power supply deficiency is represented, and therefore, the power supply surplus of the subareas A and C and the power supply deficiency of the subarea B are obtained through the analysis.
S413, determining a supply and demand prediction error based on the supply and demand deviation of the power grid partition, optimizing analysis parameters, and adopting the formula:;
Calculating a supply and demand balance error value And comparing the adjusted predicted data with the current data to obtain supply-demand balance evaluation data, wherein,Represents the firstThe actual load demands of the individual grid partitions,Represents the firstThe power supply capacity of the individual grid partitions,Representing the total number of power grid partitions;
And determining a supply and demand prediction error, namely a difference between the actual load demand and the predicted value. Assuming load demand predictions for A, B, C sections of 48 megawatts, 63 megawatts, and 69 megawatts, respectively, the prediction errors are-3 megawatts (45 MW-48 MW), 2 megawatts (65 MW-63 MW), and-1 megawatts (68 MW-69 MW), respectively, substituting the above data into the formula:
;
calculating the supply and demand balance error value The result shows that the current power grid is basically balanced in overall supply and demand, the error is small, and supply and demand balance evaluation data are obtained by comparing the adjusted predicted data with current actual data, so that a reference basis is provided for power grid dispatching and planning.
Referring to fig. 6, the steps for obtaining the power analysis deployment ready model specifically include:
s511, invoking supply and demand balance evaluation data, evaluating the power demand level, acquiring the power generation capacity of the power generation unit, and analyzing the matching degree between the power generation unit and the demand level to obtain the power supply and demand matching degree;
Acquiring real-time load data of a power grid, combining power prediction data to determine power demand levels of a plurality of time periods in future, collecting power generation capacity parameters of each power generation unit on the basis, analyzing the maximum and minimum power output ranges of the power generation units, evaluating respective adjustment rates, calculating available power of each power generation unit under different load levels, calculating the difference between power demand and available power generation power for different time points to obtain power surplus and shortage values at each time point, setting a supply and demand matching judgment threshold value, assuming that the threshold value is +/-5%, if the power surplus and shortage values are within the range, considering that the supply and demand match is reasonable, if the threshold value is exceeded, adopting power generation units with low uniform adjustment or priority calling cost to perform complementary calculation according to the power generation unit output power required to be adjusted, adjusting the load distribution of each power generation unit, and finally calculating the supply and demand matching degree, wherein the matching degree can be calculated by adopting the ratio of the supply and demand difference to the demand value, for example, the demand is 100MW at a certain time point, the power generation capacity is 95MW, and the supply and demand matching degree is 95MW Represents the basic matching of supply and demand, and if the matching degree is 110MWAnd when the power supply and demand exceeds the threshold range, the distribution load needs to be adjusted to obtain the power supply and demand matching degree.
S512, calculating unit power generation cost based on the power supply and demand matching degree and combining the power generation cost data of the power generation units, screening the power generation unit with the optimal power generation cost, and adopting the formula:;
Calculating a coefficient of unit efficiency , wherein,Represents the firstThe power generated by the power generation units,Represents the firstThe power generation cost of the individual power generation units,Represents the firstThe power requirements of the individual time periods,Representing the total number of all time periods;
First, the fuel consumption rate of each power generation unit is obtained, and the unit fuel price is combined to calculate the unit power generation cost, for example, the fuel consumption rate of a certain coal-fired power generation unit is 0.3t/MWh, the unit fuel price is 500 yuan/t, and the unit power generation cost is The unit cost of all the power generation units is calculated at the same time, the cost threshold is set to be 200 units/MWh, the power generation units with the cost lower than the threshold and meeting supply and demand matching are screened, the unit efficiency parameters are further calculated, and the formula is adopted:
The data of the coal-fired power generation unit are as follows, the power output is 80MW,90MW and 100MW (corresponding to three time periods), the unit power generation cost is 120 yuan/MWh, 110 yuan/MWh and 105 yuan/MWh, the power demand is 100MW,100MW and the total number of 100 MW-time periods is 3, and the data are substituted into the formula:
;
;
;
as a result of comparison, the coal-fired power generation unit Of gas-fired power unitsTherefore, the unit efficiency coefficient of the coal-fired power generation unit is better, and the unit efficiency coefficient is obtained by selecting the unit efficiency coefficient into a power generation unit list.
S513, based on the unit efficiency coefficient, combining the screened power generation units, creating an executable model file according to the real-time load and the power prediction data of the power grid, and acquiring a power analysis deployment ready model;
The power output range of the screened optimal power generation unit is obtained, the power adjustment range of the power generation unit under different load conditions is calculated, a load adjustment period is set, for example, power distribution is adjusted every 15 minutes, the current load level is obtained based on real-time load data, the load trend of the next adjustment period is calculated according to prediction data, for example, the current load is 200MW, the load is predicted to be increased to 210MW after 10 minutes, the power generation power which needs to be increased is calculated, power scheduling is carried out according to the power generation unit with the optimal unit efficiency coefficient, the power distribution is ensured to be in the adjustable range, an executable model file containing the load adjustment scheme of all time periods is generated, and the power analysis deployment ready model is obtained.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (5)
1. The rapid construction method of the electric power data analysis model based on the big data is characterized by comprising the following steps of:
S1, monitoring voltage amplitude, frequency offset and phase angle error based on voltage, current and power data of a transformer substation, detecting data integrity, removing abnormal data node information, and obtaining a power data processing result;
s2, collecting power load characteristics, equipment operation parameters and time sequence data according to the power data processing result, evaluating the interdependence among each characteristic, screening key characteristics of a power system, and obtaining power characteristic balanced configuration;
The step of obtaining the power characteristic balance configuration specifically comprises the following steps:
s211, collecting power load characteristics, equipment operation parameters and time sequence data according to the power data processing result, extracting the load power, equipment current and voltage change trend of each data point, analyzing the distribution condition of the characteristics in the time dimension, and obtaining power characteristic time sequence distribution;
S212, calculating a correlation coefficient between each feature based on the power feature time sequence distribution, screening features with critical interdependence, analyzing the correlation between the features and the running state of the power system, and obtaining the critical features of the power system;
S213, calling key characteristics of the power system, reformatting characteristic representation, and adopting a formula according to a standardized mean value and characteristic deviation: ;
calculating feature equality And adjusting the characteristic normalization parameters to obtain the power characteristic balance configuration, wherein,Represents the firstThe characteristic value of the electric power is calculated,Representative characteristicsIs used for the average value of (a),Representative characteristicsIs set in the standard deviation of (a),Representing the total number of characteristic data points;
S3, calculating the power change rate in a difference time window based on the power feature balance configuration, screening a time interval in which the power demand is increased, analyzing the fluctuation offset of a target time interval, and adjusting the weight of power input data to obtain a dynamic index of the power increase trend;
s4, analyzing the load parameters of the power transmission line and the power supply conditions of the power grid subareas according to the dynamic indexes of the power growth trend, judging the power supply and demand state of each subarea, and obtaining supply and demand balance evaluation data;
S5, invoking the supply-demand balance evaluation data, analyzing and screening a power generation unit with optimal efficiency, and acquiring a power analysis deployment ready model by combining real-time load and power prediction data of a power grid;
the step of acquiring the electric power analysis deployment ready model specifically comprises the following steps:
s511, calling the supply and demand balance evaluation data, evaluating the power demand level, acquiring the power generation capacity of the power generation unit, and analyzing the matching degree between the power generation unit and the demand level to obtain the power supply and demand matching degree;
S512, calculating unit power generation cost based on the power supply and demand matching degree and combining the power generation cost data of the power generation units, screening the power generation unit with the optimal power generation cost, and adopting the formula: ;
Calculating a coefficient of unit efficiency , wherein,Represents the firstThe power generated by the power generation units,Represents the firstThe power generation cost of the individual power generation units,Represents the firstThe power requirements of the individual time periods,Representing the total number of all time periods;
and S513, based on the unit efficiency coefficient, combining the screened power generation units, creating an executable model file according to the real-time load and the power prediction data of the power grid, and obtaining a power analysis deployment ready model.
2. The method for quickly constructing a big data-based power data analysis model according to claim 1, wherein the power data processing result comprises a data integrity record and an abnormal node index, the power growth trend dynamic index comprises a rate change analysis result, a growth interval identification result and a data weight condition, the supply and demand balance evaluation data specifically comprises load state information, a prediction error evaluation result and analysis parameter details, and the power analysis deployment ready model comprises power generation efficiency data, cost benefit data and load response configuration.
3. The method for quickly constructing a power data analysis model based on big data according to claim 1, wherein the step of obtaining the power data processing result specifically comprises the following steps:
s111, based on voltage, current and power data of a transformer substation, monitoring voltage amplitude, frequency offset and phase angle error, calculating amplitude offset, frequency error amount and phase angle variation amount of data nodes, screening data nodes beyond a standard range, and obtaining an abnormal data node set;
S112, invoking the abnormal data node set, recovering missing data information from the backup system by utilizing a data backtracking mechanism, performing hash value comparison, screening data nodes with unmatched hash values, and obtaining a data integrity abnormal node set;
s113, calling the data integrity abnormal point set, removing abnormal data nodes, evaluating voltage amplitude, frequency offset and phase angle error, and adopting the formula: ;
calculating data quality evaluation value And screening qualified data nodes according to the evaluation value to obtain a power data processing result, wherein,Represents the firstThe voltage amplitude of the individual data nodes,Representing the value of the voltage reference and,Represents the firstThe frequency of the individual data nodes is determined,Represents the reference value of the frequency and,Represents the firstThe phase angle of the individual data nodes is,Representing the phase angle reference value,Representing the total number of data nodes,Representing the standard deviation of the voltage data,Representing the standard deviation of the frequency data,Representing the standard deviation of the phase angle data.
4. The method for quickly constructing a power data analysis model based on big data according to claim 1, wherein the step of obtaining the dynamic index of the power growth trend is specifically:
S311, analyzing a power load curve based on the power characteristic balanced configuration, calculating a power change rate in a difference time window, continuously detecting a power change value, calculating an average change rate of power at time intervals, and generating power change data;
S312, calculating a rate increment value based on the power change data, setting a dynamic screening threshold value, and screening a time interval in which the rate increment exceeds the threshold value to obtain a power demand increase interval set;
S313, calling the power demand increase interval set, analyzing the fluctuation offset of the target time interval, adjusting the weight of the power input data, matching the current power use trend, and adopting the formula: ;
obtaining dynamic index of power growth trend , wherein,Representing the amount of change in the power input data,Representing the total number of power data points in the time interval,A weight coefficient representing the power input data,Representing the fluctuating offset of the power load curve over the target time interval,Representing the total number of data points in the fluctuation analysis,An adjustment factor representing the tendency of the shift.
5. The method for quickly constructing a power data analysis model based on big data according to claim 1, wherein the step of obtaining the supply-demand balance evaluation data specifically comprises the steps of:
s411, analyzing power transmission line load parameters based on the dynamic indexes of the power growth trend, normalizing the power transmission ratio of each group of power transmission lines, and obtaining the power transmission line load ratio;
s412, calculating the supply and demand deviation value of each subarea based on the load ratio of the power transmission line and combining the subarea power supply capacity parameter of the power grid, and judging the current power supply state to obtain the subarea supply and demand deviation value of the power grid;
S413, determining a supply and demand prediction error, optimizing analysis parameters and adopting a formula based on the supply and demand deviation of the power grid partition: ;
Calculating a supply and demand balance error value And comparing the adjusted predicted data with the current data to obtain supply-demand balance evaluation data, wherein,Represents the firstThe actual load demands of the individual grid partitions,Represents the firstThe power supply capacity of the individual grid partitions,Representing the total number of grid partitions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510670075.9A CN120196904B (en) | 2025-05-23 | 2025-05-23 | Rapid construction method of electric power data analysis model based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510670075.9A CN120196904B (en) | 2025-05-23 | 2025-05-23 | Rapid construction method of electric power data analysis model based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120196904A CN120196904A (en) | 2025-06-24 |
| CN120196904B true CN120196904B (en) | 2025-08-05 |
Family
ID=96070396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510670075.9A Active CN120196904B (en) | 2025-05-23 | 2025-05-23 | Rapid construction method of electric power data analysis model based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120196904B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949006A (en) * | 2021-02-02 | 2021-06-11 | 广东电网有限责任公司电网规划研究中心 | Power distribution planning method, system and equipment |
| CN113156247A (en) * | 2021-04-23 | 2021-07-23 | 北京建筑大学 | Early warning method and device for low-frequency oscillation of power system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114680A (en) * | 2023-08-14 | 2023-11-24 | 国网辽宁省电力有限公司电力科学研究院 | A quick traceback method for charging pile transaction data |
| CN118646015B (en) * | 2024-08-15 | 2024-10-22 | 成都太阳高科技有限责任公司 | Power grid load balancing control method and system based on big data |
| CN119518705B (en) * | 2024-10-28 | 2025-08-01 | 广州南网科研技术有限责任公司 | Intelligent electricity load management method based on big data analysis |
| CN119742803A (en) * | 2025-02-28 | 2025-04-01 | 山东国研电力股份有限公司 | Emerging load power supply potential improving method and system |
| CN119892108A (en) * | 2025-03-03 | 2025-04-25 | 广东电网有限责任公司广州供电局 | Data processing method for power dispatching system network province collaborative monitoring |
-
2025
- 2025-05-23 CN CN202510670075.9A patent/CN120196904B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949006A (en) * | 2021-02-02 | 2021-06-11 | 广东电网有限责任公司电网规划研究中心 | Power distribution planning method, system and equipment |
| CN113156247A (en) * | 2021-04-23 | 2021-07-23 | 北京建筑大学 | Early warning method and device for low-frequency oscillation of power system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120196904A (en) | 2025-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117175695B (en) | Photovoltaic micro-grid power generation method and system based on diesel generator set | |
| CN111103565B (en) | Data transformation method and system based on intelligent electric energy meter metering error analysis | |
| CN106411257A (en) | Photovoltaic power station state diagnosis method and device | |
| CN107437135B (en) | Novel energy storage type selection method | |
| CN118534830B (en) | Energy management system and method | |
| CN119051084B (en) | Dynamic load balancing optimization method and system for micro-grid based on historical electricity consumption data | |
| CN118336836B (en) | Multi-type renewable energy peak-to-peak demand analysis method based on risk elimination | |
| CN120087726B (en) | Multi-source data fusion-based optical storage collaborative optimization scheduling system and method | |
| CN120222437B (en) | Distributed energy storage power system optimization scheduling method and system | |
| CN119048283A (en) | Power dispatching optimization system based on large language model | |
| CN119362609B (en) | A method for coordinated control of multi-energy power systems at spatiotemporal scales | |
| CN120127655A (en) | Capacity prediction system of wind-solar-energy storage power station based on multi-objective | |
| CN117892939A (en) | Power plant energy consumption control method and system based on energy Internet | |
| Wang et al. | Multi-time scale optimal configuration of user-side energy storage considering demand perception | |
| CN117791626B (en) | Intelligent comprehensive power box power supply optimization method | |
| CN120196904B (en) | Rapid construction method of electric power data analysis model based on big data | |
| CN118798548A (en) | Edge-to-edge integrated management platform for distributed energy | |
| CN117610234B (en) | Time sequence production simulation method and system based on energy interconnection | |
| CN115656914B (en) | Intelligent ammeter metering accuracy detection method and device based on big data | |
| CN118432044A (en) | Source network collaborative planning method and system for modifying flexibility of power system unit | |
| CN117634872A (en) | Risk early warning system and method for new energy power system | |
| CN112613670A (en) | Device and method for predicting power consumer demand based on weight distribution | |
| Ji et al. | A novel combinational evaluation method of voltage and reactive power in regional power grid containing renewable energy | |
| CN120258247B (en) | A method and device for spatiotemporal prediction of medium- and long-term capacity demand of distributed energy storage in distribution networks | |
| CN118100318B (en) | A method and system for ensuring safe power supply based on new energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |