CN104037943B - A kind of voltage monitoring method and system that improve grid voltage quality - Google Patents
A kind of voltage monitoring method and system that improve grid voltage quality Download PDFInfo
- Publication number
- CN104037943B CN104037943B CN201410273793.4A CN201410273793A CN104037943B CN 104037943 B CN104037943 B CN 104037943B CN 201410273793 A CN201410273793 A CN 201410273793A CN 104037943 B CN104037943 B CN 104037943B
- Authority
- CN
- China
- Prior art keywords
- voltage
- quality
- index
- time section
- monitoring point
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a kind of voltage monitoring method that improves grid voltage quality, comprising: real-time voltage data and the voltage statistic data of obtaining multiple monitoring points; According to the voltage statistic data of each monitoring point collecting, the account of the history of quality of voltage index is analyzed; According to the real-time voltage data of current each monitoring point collecting, the future trend of quality of voltage index is carried out to on-line prediction. Realize the grid voltage quality monitoring system of the method, comprise data capture unit, historical time section quality of voltage index analysis unit, future time section quality of voltage index prediction unit and data storage cell. The present invention has realized the in-depth analysis to quality of voltage and the timely judgement to grid voltage quality future trend, has improved the significant degree of grid voltage quality monitoring.
Description
Technical field
The present invention relates to grid voltage quality monitoring technical field, relate in particular to a kind of voltage monitoring side of improving grid voltage qualityMethod and system.
Background technology
Along with the sustained and rapid development of national economy and improving constantly of living standards of the people, very fast the becoming of increasing of Electricity DemandGesture can not change in a long time. The development of electrical network, the continuous growth of supply load, if voltage pulsation exceedes allowed bandAnd when the time is longer, will produce greatly harm: for power supply grid, low-voltage can affect the ability of generation and supply electric equipment, impact suppliesElectricity reliability; For consumer, spread of voltage, affects service life, even burns, and increases line loss. Above-mentioned various formerBecause meeting also brings harmful effect to the normal electricity consumption of power consumer, therefore strengthen line voltage Real-Time Monitoring and data management analysis,For improving, quality of voltage is particularly important.
There are some patents monitoring and analysis aspect to quality of voltage at present, as " 200910164280.9 is (a kind of based on voltage stabilizationProperty local indexes Network Voltage Stability on-line monitoring method) " according to the topological structure of electric ginseng in the node adjacent area of point being monitoredNumber and interdependent node electric current and voltage phasor, calculate point being monitored single power consumption and transmit equivalent systematic parameter, to the voltage of monitoring pointStability judges early warning, effectively realizes the on-line real time monitoring of Network Voltage Stability. " 201210034024.X (a kind of electricityPress the method for supervising of quality) " first the quality of voltage data of the each electric pressure of regional power grid are gathered, by the analysis to data,Adopt different measure, analyze and judge supply voltage quality index, provide corresponding adjustment scheme, be conducive to tackle Adaptability AnalysisOccasion. " 201310376476.0 (a kind of wide region range self-adapting voltage quality monitoring method) " adopts voltage with each by calculatingThe voltage deviation rate of nominal voltage, carries out intellectual analysis to the voltage deviation rate result of continuous calculating, derives the volume of current systemDetermine voltage, realize voltage monitoring range self-adapting, in the situation without manual intervention, complete voltage quality monitoring." 201310528971.9 (a kind of method of the on-line prediction power system steady state voltage stability limit) " sample dimensionality reduction based on LassoThe screening sample method of method, Self-Organizing Feature Maps and error back propagation type neutral net are to power system static voltageStability limit is carried out off-line training and on-line prediction, effectively improve the off-line training efficiency of error back propagation type neutral net andLine prediction effect. Above-mentioned patent is not analysed in depth grid voltage quality index, more not to grid voltage quality in futureTrend make timely judgement, be therefore difficult to grid voltage quality to carry out effective monitoring.
Summary of the invention
The deficiency existing for prior art, the invention provides a kind of voltage monitoring method and system that improve grid voltage quality.
Technical scheme of the present invention is:
A voltage monitoring method that improves grid voltage quality, comprises the following steps:
Step 1: real-time voltage data and the voltage statistic data of obtaining multiple monitoring points;
Described voltage statistic data comprise monitoring point voltage day statistics, voltage moon statistics, voltage season statistics,The indicator-specific statistics data of the annual statistical indicator of voltage and departments at different levels;
Wherein, data when the voltage moon, statistics comprised of that month voltage statistic value, last month voltage statistic value, of that month typical case day, onData, of that month voltage reliability data when month typical case day, last month voltage reliability data, of that month power-failure counting value and have a power failure last monthStatistical value; The annual statistical indicator of voltage comprises voltage year qualification rate, the annual super upper limit rate of voltage and the annual super lower limit rate of voltage;The indicator-specific statistics data of departments at different levels comprise day qualification rate statistics, month qualification rate statistics, the season qualification rate statistics of departments at different levelsWith year qualification rate statistics;
Step 2: according to the voltage statistic data of each monitoring point collecting, the account of the history of quality of voltage index is dividedAnalyse;
Step 2-1: the monitoring point of selecting to need analysis;
Step 2-2: select to need the quality of voltage index analyzed, quality of voltage index comprise rate of qualified voltage, voltage standard poor andVoltage probability density;
Step 2-3: select year quarterly, year monthly, season monthly or the moon analysis mode per diem, select tool according to selected analysis modeThe historical time section of body;
Step 2-4: calculate the voltage matter of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionFigureofmerit value;
Step 2-5: the quality of voltage desired value that shows selected monitoring point with the form of form, curve and excellent figure;
Step 2-6: according to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value, determine voltage matterThe monitoring point that figureofmerit is poor, reports to the police, so that electric power personnel carry out diagnostic process to the quality of voltage abnormal conditions of this monitoring point;
Step 3: according to the real-time voltage data of current each monitoring point collecting, the future trend of quality of voltage index is enteredRow on-line prediction;
Step 3-1: the monitoring point of selecting to need prediction;
Step 3-2: the quality of voltage index of selecting to need prediction;
Step 3-3: select year quarterly, year monthly, season monthly or the moon prediction mode per diem, select according to the prediction mode of selectingConcrete future time section;
Step 3-4: in the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, the electricity to disappearancePress quality index data to supplement;
Step 3-5: set up the future trend on-line prediction model of quality of voltage index, being input as from current time to certain of this modelQuality of voltage desired value in the scope during this period of time of individual historical juncture, this model is output as the electricity of the future time section that will predictPress quality index value;
Step 3-6: the quality of voltage of selected monitoring point is referred to according to the future trend on-line prediction model of the quality of voltage index of setting upTarget future trend is predicted;
Step 3-7: quality of voltage index future trend online pre-that shows selected monitoring point with the form of form, curve and excellent figureSurvey result;
Step 3-8: refer to according to the on-line prediction result of the quality of voltage index future trend of selected monitoring point, each voltage gradation qualityMark setting value, the monitoring point of definite following moment quality of voltage index error, carries out early warning, so that electric power personnel are to existing voltage matterAdvanced processing is carried out in the monitoring point of amount potential problem.
The future trend on-line prediction model of setting up quality of voltage index in step 3-5 carries out as follows:
Step 3-5-1: Time Created series model, time series models be input as this from current time to certain historical junctureQuality of voltage desired value in section time range, time series models are output as the quality of voltage index of the future time section that will predictValue;
Step 3-5-2: set up gray model, gray model be input as the model during this period of time from current time to certain historical junctureQuality of voltage desired value in enclosing, gray model output is the quality of voltage desired value of the future time section that will predict;
Step 3-5-3: set up combination forecasting, the input of combination forecasting comprises the future time of time series models predictionThe quality of voltage desired value of the quality of voltage desired value of section and the future time section of Grey Model, the output of combination forecastingFor the quality of voltage desired value of future time section of time series models prediction and the voltage matter of the future time section of Grey ModelThe weighting sum of figureofmerit value, i.e. the quality of voltage desired value of the future time section of combination forecasting prediction;
Step 3-5-4: set up BP neural network model, the combination forecasting that is input as of BP neural network model is predicted notCarry out the quality of voltage desired value of time period, BP neural network model is output as the future time section of combination forecasting predictionThe error of quality of voltage desired value;
Step 3-5-5: set up the future trend on-line prediction model of quality of voltage index, the input of this model comprises combined prediction mouldThe future of the combination forecasting prediction of the quality of voltage desired value of the future time section of type prediction and the output of BP neural network modelThe error of the quality of voltage desired value of time period, on-line prediction model is output as the future time section of combination forecasting predictionThe quality of voltage index of the future time section of the combination forecasting prediction of quality of voltage desired value and the output of BP neural network modelThe error sum of value, i.e. predicting the outcome of quality of voltage index.
The monitoring point that selection described in the mode of the monitoring point that the selection described in step 2-1 need to be analyzed and step 3-1 need to be predictedMode include select single monitoring point, select multiple monitoring points, once select all relevant monitoring points of circuit, once selectAll monitoring points of transformer station and once select all monitoring points of power supply administration of county.
Described quality of voltage index comprises the poor and voltage probability density of rate of qualified voltage, voltage standard.
Described in step 2-3, select concrete historical time section according to selected analysis mode, when analysis mode is year quarterly time,Historical time section is chosen as year; When analysis mode is year monthly time, historical time section is chosen as year; When analysis mode be season monthlyTime, historical time section is chosen as time and season; When analysis mode is the moon per diem time, historical time section is chosen as time and month.
The prediction mode according to selecting described in step 3-3 is selected concrete future time section, when prediction mode be year quarterly time,The residue season that time under predicting the outcome is the current year; When prediction mode is year monthly time, the time under predicting the outcome isThe residue month in the current year; When prediction mode is season monthly time, the residue month that the time under predicting the outcome is current season; WhenPrediction mode is the moon per diem time, the residue number of days that the time under predicting the outcome is this month.
The quality of voltage achievement data to disappearance described in step 3-4 supplements the cubic spline interpolation method that adopts.
Realize the grid voltage quality monitoring system of the monitoring method of described raising grid voltage quality, comprise data capture unit,Historical time section quality of voltage index analysis unit, future time section quality of voltage index prediction unit and data storage cell;
Data capture unit is for obtaining real-time voltage data and the voltage statistic data of monitoring point;
Historical time section quality of voltage index analysis unit is used for the statistical number of each monitoring point obtaining according to data capture unitAccording to, the account of the history of quality of voltage index is analyzed, comprising: select the monitoring point of needs analysis and the voltage that needs are analyzedQuality index; Select year quarterly, year monthly, season monthly or the moon analysis mode per diem select concrete according to selected analysis modeHistorical time section; Calculate the voltage of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionQuality index value; Show the quality of voltage desired value of selected monitoring point with the form of form, curve and excellent figure; According to selected monitoringThe quality of voltage desired value of point, each voltage gradation quality index set value, and determine the monitoring point of quality of voltage index error, reportAlert;
Future time section quality of voltage index prediction unit is for according to the real-time voltage data of current each monitoring point obtaining, rightThe future trend of quality of voltage index is carried out on-line prediction, comprising: select the monitoring point of needs prediction and the voltage matter of needs predictionFigureofmerit; Select year quarterly, year monthly, season monthly or the moon prediction mode per diem select concrete according to the prediction mode of selectingFuture time section; In the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, to disappearanceQuality of voltage achievement data supplements; Set up the future trend on-line prediction model of quality of voltage index, being input as of this modelQuality of voltage desired value in scope during this period of time from current time to certain historical juncture, this model is output as and will predictsThe quality of voltage desired value of future time section; According to the future trend on-line prediction model of quality of voltage index of setting up to selected prisonThe future trend of the quality of voltage index of measuring point is predicted; Show the electricity of selected monitoring point with the form of form, curve and excellent figurePress the on-line prediction result of quality index future trend; According to the on-line prediction of the quality of voltage index future trend of selected monitoring pointResult, each voltage gradation quality index setting value, determine that early warning is carried out in the monitoring point of future time section quality of voltage index error;
Data storage cell is for becoming the future of storing the real-time voltage data of monitoring point and voltage statistic data, quality of voltage indexGesture on-line prediction model parameter, monitoring point in every quality of voltage desired value of each historical time section and monitoring point at future timeThe quality of voltage index prediction value of section.
Described historical time section quality of voltage index analysis unit comprises historical time section quality of voltage desired value computing module and historyTime period quality of voltage index analysis shows and alarm module;
Historical time section quality of voltage desired value computing module is for selecting to need the monitoring point of analyzing, the quality of voltage that needs analysisIndex and analysis mode, select concrete historical time section according to selected analysis mode, and then calculate selected monitoring point in this historyThe quality of voltage desired value of time period;
Historical time section quality of voltage index analysis shows and alarm module shows selected for the form with form, curve and excellent figureThe quality of voltage desired value of monitoring point; According to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value,Determine the monitoring point of quality of voltage index error, report to the police.
Described future time section quality of voltage index prediction unit comprises that monitoring point historical data complementary module, time series models buildFormwork erection piece, gray model are set up module, combination forecasting is set up module, BP Establishment of Neural Model module, voltage matterFigureofmerit prediction module, quality of voltage index prediction result show and warning module;
Monitoring point historical data complementary module is for selecting to need the monitoring point of prediction, quality of voltage index and the prediction that need to predictMode, selects concrete future time section, the voltage matter when selected monitoring point in historical time section according to the prediction mode of selectingWhen figureofmerit data exist disappearance, the quality of voltage achievement data of disappearance is supplemented;
Time series models are set up module for setting up with the voltage in the scope during this period of time from current time to certain historical junctureQuality index value is input, the time series models taking the quality of voltage desired value of the future time section that will predict as output;
Gray model is set up module for setting up with the quality of voltage in the scope during this period of time from current time to certain historical junctureDesired value is input, gray model taking the quality of voltage desired value of the future time section that will predict as output;
Combination forecasting set up module for setting up with the quality of voltage desired value of the future time section of time series models predictions andThe quality of voltage desired value of the future time section of Grey Model is input, with the future time section of time series models predictionsThe weighting sum of the quality of voltage desired value of the future time section of quality of voltage desired value and Grey Model is that the combination of output is pre-Survey model;
BP Establishment of Neural Model module is for setting up the quality of voltage index with the future time section of combination forecasting predictionThe error of the quality of voltage desired value of the future time section that value is predicted for input, taking combination forecasting is the BP nerve net of outputNetwork model;
Quality of voltage index prediction module for setting up with the quality of voltage desired value of the future time section of combination forecasting prediction andThe error of the quality of voltage desired value of the future time section of the combination forecasting prediction of BP neural network model output for input,With the quality of voltage desired value of future time section and the combined prediction mould of BP neural network model output of combination forecasting predictionThe error sum of the quality of voltage desired value of the future time section of type prediction is that the future trend of quality of voltage index of output is pre-onlineSurvey model, and according to the future trend on-line prediction model of quality of voltage index of setting up the quality of voltage index to selected monitoring pointFuture trend predict, obtain predicting the outcome of quality of voltage index;
Quality of voltage index prediction result shows and warning module is used for showing selected monitoring point with the form of form, curve and excellent figureThe on-line prediction result of quality of voltage index future trend, and according to the quality of voltage index future trend of selected monitoring pointLine predicts the outcome, each voltage gradation quality index setting value, determines the monitoring point of following moment quality of voltage index error, carries out pre-Alert.
Beneficial effect:
Quality of voltage is not analysed in depth and not to grid voltage quality for current grid voltage quality monitoring methodFuture trend make the problem that timely judgement causes being difficult to grid voltage quality to carry out effective monitoring, the present invention proposes oneBased on the monitoring method that improves grid voltage quality, comprise data acquisition, monitoring point historical juncture quality of voltage Monitoring Indexes, baseIn the following moment quality of voltage index prediction in the monitoring point of combination forecasting and BP neural network model. Realize voltage matterThe in-depth analysis of amount and the timely judgement to grid voltage quality future trend, improved the significant degree of grid voltage quality monitoring.
Brief description of the drawings
Fig. 1 is the structured flowchart of the monitoring system of the raising grid voltage quality of the specific embodiment of the invention;
Fig. 2 is the flow chart of the monitoring method of the raising grid voltage quality of the specific embodiment of the invention;
Fig. 3 be the specific embodiment of the invention improve the monitoring point voltage standard of monitoring method of grid voltage quality poor year monthlyMonitoring result curve;
Fig. 4 be poor year of the monitoring point voltage standard of monitoring method of the raising grid voltage quality of the specific embodiment of the invention byThe monitoring result rod figure of the moon;
Fig. 5 is two monitoring point rate of qualified voltage of the monitoring method of the raising grid voltage quality of the specific embodiment of the inventionYear monitoring result curve monthly;
Fig. 6 is that a kind of two monitoring point voltages of the monitoring method that improves grid voltage quality of the specific embodiment of the invention are qualifiedThe year monitoring result monthly of rate;
Fig. 7 is the flow chart that the account of the history to quality of voltage index of the specific embodiment of the invention is analyzed;
Fig. 8 be the specific embodiment of the invention the future trend of quality of voltage index is carried out to the flow chart of on-line prediction;
Fig. 9 is the flow chart of the future trend on-line prediction model of setting up quality of voltage index of the specific embodiment of the invention.
Detailed description of the invention
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is elaborated.
In present embodiment, improve the grid voltage quality monitoring system of the monitoring method of grid voltage quality, as shown in Figure 1,Comprise data capture unit, historical time section quality of voltage index analysis unit, future time section quality of voltage index prediction unitAnd data storage cell;
Data capture unit is for obtaining real-time voltage data and the voltage statistic data of monitoring point;
Historical time section quality of voltage index analysis unit is used for the statistical number of each monitoring point obtaining according to data capture unitAccording to, the account of the history of quality of voltage index is analyzed, comprising: select the monitoring point of needs analysis and the voltage that needs are analyzedQuality index; Select year quarterly, year monthly, season monthly or the moon analysis mode per diem select concrete according to selected analysis modeHistorical time section; Calculate the voltage of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionQuality index value; Show the quality of voltage desired value of selected monitoring point with the form of form, curve and excellent figure; According to selected monitoringThe quality of voltage desired value of point, each voltage gradation quality index set value, and determine the monitoring point of quality of voltage index error, reportAlert;
Future time section quality of voltage index prediction unit is for according to the real-time voltage data of current each monitoring point obtaining, rightThe future trend of quality of voltage index is carried out on-line prediction, comprising: select the monitoring point of needs prediction and the voltage matter of needs predictionFigureofmerit; Select year quarterly, year monthly, season monthly or the moon prediction mode per diem select concrete according to the prediction mode of selectingFuture time section; In the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, to disappearanceQuality of voltage achievement data supplements; Set up the future trend on-line prediction model of quality of voltage index, being input as of this modelQuality of voltage desired value in scope during this period of time from current time to certain historical juncture, this model is output as and will predictsThe quality of voltage desired value of future time section; According to the future trend on-line prediction model of quality of voltage index of setting up to selected prisonThe future trend of the quality of voltage index of measuring point is predicted; Show the electricity of selected monitoring point with the form of form, curve and excellent figurePress the on-line prediction result of quality index future trend; According to the on-line prediction of the quality of voltage index future trend of selected monitoring pointResult, each voltage gradation quality index setting value, determine that early warning is carried out in the monitoring point of future time section quality of voltage index error;
Data storage cell is for becoming the future of storing the real-time voltage data of monitoring point and voltage statistic data, quality of voltage indexGesture on-line prediction model parameter, monitoring point in every quality of voltage desired value of each historical time section and monitoring point at future timeThe quality of voltage index prediction value of section.
Historical time section quality of voltage index analysis unit comprises historical time section quality of voltage desired value computing module and historical timeSection quality of voltage index analysis shows and alarm module;
Historical time section quality of voltage desired value computing module is for selecting to need the monitoring point of analyzing, the quality of voltage that needs analysisIndex and analysis mode, select concrete historical time section according to selected analysis mode, and then calculate selected monitoring point in this historyThe quality of voltage desired value of time period;
Historical time section quality of voltage index analysis shows and alarm module shows selected for the form with form, curve and excellent figureThe quality of voltage desired value of monitoring point; According to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value,Determine the monitoring point of quality of voltage index error, report to the police.
Future time section quality of voltage index prediction unit comprises that monitoring point historical data complementary module, time series models set up mouldPiece, gray model are set up module, combination forecasting and are set up module, BP Establishment of Neural Model module, quality of voltage and refer toMark prediction module, quality of voltage index prediction result show and warning module;
Monitoring point historical data complementary module is for selecting to need the monitoring point of prediction, quality of voltage index and the prediction that need to predictMode, selects concrete future time section, the voltage matter when selected monitoring point in historical time section according to the prediction mode of selectingWhen figureofmerit data exist disappearance, the quality of voltage achievement data of disappearance is supplemented;
Time series models are set up module for setting up with the voltage in the scope during this period of time from current time to certain historical junctureQuality index value is input, the time series models taking the quality of voltage desired value of the future time section that will predict as output;
Gray model is set up module for setting up with the quality of voltage in the scope during this period of time from current time to certain historical junctureDesired value is input, gray model taking the quality of voltage desired value of the future time section that will predict as output;
Combination forecasting set up module for setting up with the quality of voltage desired value of the future time section of time series models predictions andThe quality of voltage desired value of the future time section of Grey Model is input, with the future time section of time series models predictionsThe weighting sum of the quality of voltage desired value of the future time section of quality of voltage desired value and Grey Model is that the combination of output is pre-Survey model;
BP Establishment of Neural Model module is for setting up the quality of voltage index with the future time section of combination forecasting predictionThe error of the quality of voltage desired value of the future time section that value is predicted for input, taking combination forecasting is the BP nerve net of outputNetwork model;
Quality of voltage index prediction module for setting up with the quality of voltage desired value of the future time section of combination forecasting prediction andThe error of the quality of voltage desired value of the future time section of the combination forecasting prediction of BP neural network model output for input,With the quality of voltage desired value of future time section and the combined prediction mould of BP neural network model output of combination forecasting predictionThe error sum of the quality of voltage desired value of the future time section of type prediction is that the future trend of quality of voltage index of output is pre-onlineSurvey model, and according to the future trend on-line prediction model of quality of voltage index of setting up the quality of voltage index to selected monitoring pointFuture trend predict, obtain predicting the outcome of quality of voltage index;
Quality of voltage index prediction result shows and warning module is used for showing selected monitoring point with the form of form, curve and excellent figureThe on-line prediction result of quality of voltage index future trend, and according to the quality of voltage index future trend of selected monitoring pointLine predicts the outcome, each voltage gradation quality index setting value, determines the monitoring point of following moment quality of voltage index error, carries out pre-Alert.
In present embodiment, improve the voltage monitoring method of grid voltage quality, its flow process as shown in Figure 2, comprises the following steps:
Step 1: real-time voltage data and the voltage statistic data of obtaining multiple monitoring points;
Real-time voltage data comprise 5 minutes real-time voltage data;
Voltage statistic data comprise voltage day statistics, voltage moon statistics, voltage season statistics, the electricity of monitoring pointPress the indicator-specific statistics data of annual statistical indicator and departments at different levels;
Wherein, data when the voltage moon, statistics comprised of that month voltage statistic value, last month voltage statistic value, of that month typical case day, onWhen month typical case day the indicator-specific statistics data of data, of that month electric departments at different levels press reliability data, last month voltage reliability data, whenMonth power-failure counting value and last month power-failure counting value; The annual statistical indicator of voltage comprises voltage year qualification rate, the annual super upper limit of voltageThe annual super lower limit rate of rate and voltage; The indicator-specific statistics data of departments at different levels comprise closes the day qualification rate statistics of departments at different levels, the moonLattice rate statistics, season qualification rate statistics and year qualification rate statistics; Departments at different levels comprise transformer station, power supply station, Zi Kong district, county's power supplyOffice and regional power office;
Step 2: according to the voltage statistic data of each monitoring point collecting, the account of the history of quality of voltage index is dividedAnalyse, as shown in Figure 7;
Step 2-1: the monitoring point of selecting to need analysis;
Select the mode that needs the monitoring point of analyzing to comprise the single monitoring point of selection, select multiple monitoring points, once select circuit instituteThere is relevant monitoring point, once select all monitoring points of transformer station and once select all monitoring points of power supply administration of county.
Step 2-2: select to need the quality of voltage index analyzed, quality of voltage index comprise rate of qualified voltage, voltage standard poor andVoltage probability density;
Step 2-3: select year quarterly, year monthly, season monthly or the moon analysis mode per diem, select tool according to selected analysis modeThe historical time section of body;
When analysis mode is year quarterly time, historical time section is chosen as year; When analysis mode is year monthly time, historical time Duan XuanBe selected as year; When analysis mode is season monthly time, historical time section is chosen as time and season; When analysis mode is the moon per diem time,Historical time section is chosen as time and month.
Step 2-4: calculate the voltage matter of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionFigureofmerit value;
Rate of qualified voltage=(1-voltage overtime/total operating statistic time) * 100%;
When s is that when day, voltage standard was poor, n is the quantity of sampled point in a day,For per day electricityPress; When s is that when the moon, voltage standard was poor, n is the number of days in January;For monthly average voltage; When s is when year, voltage standard was poor,N is 12;For annual voltage;
Voltage density variation=∫ (g (x)-h (x)) dx, x represents magnitude of voltage, g (x) is virtual voltage probability density distribution, h (x)The expectation voltage obtaining for historical voltage data distributes.
Step 2-5: the quality of voltage desired value that shows selected monitoring point with the form of form, curve and excellent figure;
Present embodiment shows that with the form of form the voltage standard of selected monitoring point is poor in table 1:
The quality of voltage desired value of the selected monitoring point of table 1
Time | Monitoring point numbering | Monitoring point title | Voltage indexes title | Voltage indexes value | Evaluate |
In January, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.32 | Better |
In February, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.66 | Better |
In March, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.01 | Better |
In April, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.16 | Better |
In May, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.07 | Better |
In June, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.41 | Better |
In July, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 2.12 | Better |
In August, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 3.22 | Generally |
In September, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 0.96 | Better |
In October, 2011 | 02010101010000001 | No. 1 LAN monitoring point | Voltage standard is poor | 39.34 | Poor |
The quality of voltage desired value that present embodiment shows selected monitoring point with the form of curve as shown in Figure 3, the curve in this figureThe fraction of the year of being 2011, the voltage standard of the moon is poor; The quality of voltage desired value that shows selected monitoring point with the form of excellent figure as shown in Figure 4.
Step 2-6: according to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value, determine voltage matterThe monitoring point that figureofmerit is poor, reports to the police, so that electric power personnel carry out diagnostic process to the quality of voltage abnormal conditions of this monitoring point;
Each voltage gradation standard deviation requirement setting value is: good: [0,1); Better: [1,3); General: [3,10); Poor: [10,20);Poor [20 ,+∞).
According to the above results, what can be perfectly clear finds out that monitoring point is at the poor index extreme difference of the voltage standard in October, 2011,Carry out alarm indication, instruct electric power personnel to monitoring point in October, 2011 quality of voltage situation investigate, realize to voltageThe in-depth analysis of quality;
Step 3: according to the real-time voltage data of current each monitoring point collecting, the future trend of quality of voltage index is enteredRow on-line prediction, as shown in Figure 8;
Step 3-1: the monitoring point of selecting to need prediction;
Select the mode of the monitoring point that needs prediction to comprise the single monitoring point of selection, select multiple monitoring points, once select circuit instituteThere is relevant monitoring point, once select all monitoring points of transformer station and once select all monitoring points of power supply administration of county.
Step 3-2: the quality of voltage index of selecting to need prediction;
Step 3-3: select year quarterly, year monthly, season monthly or the moon prediction mode per diem, select according to the prediction mode of selectingConcrete future time section;
When prediction mode is year quarterly time, the residue season that the time under predicting the outcome is the current year; When prediction mode is for press in yearWhen the moon, the residue month that the time under predicting the outcome is the current year; When prediction mode is season monthly time, under predicting the outcomeTime is the residue month of current season; When prediction mode is the moon per diem time, the residue number of days that the time under predicting the outcome is this month;
Step 3-4: in the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, the electricity to disappearancePress quality index data to supplement;
The method that data filling adopts is cubic spline interpolation algorithm, cubic spline functions S (x) ∈ C2[a,b],a=x0<x1<...<xn=b,yj=f(xj), S (x) is at each minizone [xj,xj+1] on be cubic polynomial: Sj(x)=ajx3+bjx2+cjx+djj=0,1,...,n-1
Wherein aj,bj,cj,djUndetermined, and it is met:
S(xj)=yjj=0,1,...,n
Wherein xjRepresent j node in interval [a, b], yjRepresent node xjCorresponding functional value, S (xj) three samples of expressionBar interpolating function is at node xjCorresponding functional value,Represent that S (x) is at node xjLimiting value,RepresentS (x) is at node xjThe limiting value of first derivative,Represent that S (x) is at node xjThe limiting value of second dervative, S'(xj) tableShow that S (x) is at node xjFirst derivative, S " (xj) represent that S (x) is at node xjSecond dervative.
Step 3-5: set up the future trend on-line prediction model of quality of voltage index, being input as from current time to certain of this modelQuality of voltage desired value in the scope during this period of time of individual historical juncture, this model is output as the electricity of the future time section that will predictPress quality index value, as shown in Figure 9;
Step 3-5-1: Time Created series model, time series models be input as this from current time to certain historical junctureQuality of voltage desired value in section time range, time series models are output as the quality of voltage index of the future time section that will predictValue;
In present embodiment, time series models adopt ARIMA (p, d, q) model, wherein p, and d, q represents respectively autoregression modelThe exponent number of exponent number, difference order and moving average model(MA model). Come this sequence of approximate description, its representation by Mathematical ModelingFor:
Wherein, XtFor known variables,For hysteresis operator, ajRepresent Parameters of Autoregressive Models coefficient, bjRepresent rolling average mouldShape parameter, εtRepresent independent identically distributed sequence of random variables.
Step 3-5-2: set up gray model, gray model be input as the model during this period of time from current time to certain historical junctureQuality of voltage desired value in enclosing, gray model output is the quality of voltage desired value of the future time section that will predict;
(1) by primary voltage quality index value sequence X(0)=[x(0)(1),x(0)(2),...,x(0)(n)] obtain X(1)=[x(1)(1),x(1)(2),...,x(1)(n)], x wherein(0)(i) > 0 (i=1,2 ..., n) represent quality of voltage desired value;
(2) the cumulative matrix B of structure and constant term vector Yn,
(3) solve grey parameter by least square method:
(4) albinism differential equation corresponding to GM (1,1) model is:
(5) by grey parameter substitution time respective function: Also cumulativeFormer obtaining
(6) right Reduction differentiate obtains predictive equation:
Step 3-5-3: set up combination forecasting, the input of combination forecasting comprises the future time of time series models predictionThe quality of voltage desired value of the quality of voltage desired value of section and the future time section of Grey Model, the output of combination forecastingFor the quality of voltage desired value of future time section of time series models prediction and the voltage matter of the future time section of Grey ModelThe weighting sum of figureofmerit value, i.e. the quality of voltage desired value of the future time section of combination forecasting prediction;
Combination forecasting:
Wherein t=1,2 ..., n, the quality of voltage index actual observed value of t phase is xt,w1For the weight coefficient of time series models,w2For the weight coefficient of gray model,Be the quality of voltage index prediction value of t phase time series models,It is t phase greyThe quality of voltage index prediction value of model. Determining as follows of weight coefficient:
In formula, ejThe error mean square that is j model (j=1 represents time series models, and j=2 represents gray model) is poor,
Step 3-5-4: set up BP neural network model, the combination forecasting that is input as of BP neural network model is predicted notCarry out the quality of voltage desired value of time period, BP neural network model is output as the future time section of combination forecasting predictionThe error of quality of voltage desired value;
(1) determine the network number of plies: the three-layer network that adopts single hidden layer;
(2) determine each layer of neuronic number of network: selecting input layer number is 4, and output layer neuron number is 1, setThe start node number of hidden layer is 2;
(3) sample is selected and data pretreatment: the quality of voltage achievement data obtaining is divided into groups, and one group of quality of voltage index numberAccording to being used for composing training sample, another group quality of voltage achievement data forms test samples, for fear of between data because of the order of magnitudeDifference, compared with causing neural network forecast error larger greatly, need to be normalized input voltage quality index sample data:Wherein XtFor raw sample data, Xmax,XminBe respectively original variable XtIn maximum and minimumValue; StFor XtValue after conversion;
Model training: getting hidden layer excitation function is logarithm S type function, and output layer excitation function is pure linear function, chooses instructionPracticing function is that momentum gradient declines and adaptive learning speed training function, and learning function is momentum gradient decline learning function. WithTraining sample, according to the step of neural network algorithm, carries out repetition training to network, until network convergence is in certain standard. No, repeat to change the initial weight of network, even topology of networks, until training result is satisfied, is combinedThe error of the quality of voltage desired value of the future time section of forecast model prediction.
Step 3-5-5: set up the future trend on-line prediction model of quality of voltage index, the input of this model comprises combined prediction mouldThe future of the combination forecasting prediction of the quality of voltage desired value of the future time section of type prediction and the output of BP neural network modelThe error of the quality of voltage desired value of time period, on-line prediction model is output as the future time section of combination forecasting predictionThe quality of voltage index of the future time section of the combination forecasting prediction of quality of voltage desired value and the output of BP neural network modelThe error sum of value, i.e. predicting the outcome of quality of voltage index.
With weighted array forecast model, quality of voltage index sample data is predicted, and obtained quality of voltage index prediction valueWith quality of voltage index prediction error e, obtain the predicted value of quality of voltage index prediction deviation e with neural network modelObtainFinal quality of voltage index prediction result.
Step 3-6: the quality of voltage of selected monitoring point is referred to according to the future trend on-line prediction model of the quality of voltage index of setting upTarget future trend is predicted;
Step 3-7: quality of voltage index future trend online pre-that shows selected monitoring point with the form of form, curve and excellent figureSurvey result;
Present embodiment shows selected monitoring point rate of qualified voltage with the form of form is in table 2:
The rate of qualified voltage of the selected monitoring point of table 2
Time | Monitoring point numbering | Monitoring point title | Voltage indexes title | Voltage indexes value | Evaluate |
In January, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 96.88% | Generally |
In February, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 96.78% | Generally |
In March, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 97.08% | Generally |
In April, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 97.98% | Generally |
In May, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 96.58% | Generally |
In June, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 97.98% | Generally |
In July, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 97.98% | Generally |
In August, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 96.58% | Generally |
In September, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 94.62% | Generally |
In October, 2011 | 02010101010000002 | No. 2 LAN monitoring points | Rate of qualified voltage | 98.47% | Better |
In January, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 97.08% | Generally |
In February, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 96.88% | Generally |
In March, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 96.78% | Generally |
In April, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 96.58% | Generally |
In May, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 96.58% | Generally |
In June, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 97.98% | Generally |
In August, 2011 | 02010101010000004 | No. 4 LAN monitoring points | Rate of qualified voltage | 70.56% | Poor |
Step 3-8: refer to according to the on-line prediction result of the quality of voltage index future trend of selected monitoring point, each voltage gradation qualityMark setting value, the monitoring point of definite following moment quality of voltage index error, carries out early warning, so that electric power personnel are to existing voltage matterAdvanced processing is carried out in the monitoring point of amount potential problem.
Each grade presses qualification rate target setting value to be: good: (99.5%, 100%]; Better: (98.0%, 99.5%]; General:(90.0%, 98.0%]; Poor: (80.0%, 90.0%]; Poor (0,90.0%].
According to above-mentioned demonstration result, what can be perfectly clear finds out No. 4 LAN monitoring points rate of qualified voltage in August, 2011Index extreme difference, carry out early warning demonstration, instruct electric power personnel to investigate in advance the quality of voltage situation of No. 4 LAN monitoring points,Improve the significant degree of grid voltage quality monitoring.
Claims (9)
1. a voltage monitoring method that improves grid voltage quality, is characterized in that, comprises the following steps:
Step 1: real-time voltage data and the voltage statistic data of obtaining multiple monitoring points;
Described voltage statistic data comprise monitoring point voltage day statistics, voltage moon statistics, voltage season statistics,The indicator-specific statistics data of the annual statistical indicator of voltage and departments at different levels;
Wherein, data when the voltage moon, statistics comprised of that month voltage statistic value, last month voltage statistic value, of that month typical case day, onData, of that month voltage reliability data when month typical case day, last month voltage reliability data, of that month power-failure counting value and have a power failure last monthStatistical value; The annual statistical indicator of voltage comprises voltage year qualification rate, the annual super upper limit rate of voltage and the annual super lower limit rate of voltage;The indicator-specific statistics data of departments at different levels comprise day qualification rate statistics, month qualification rate statistics, the season qualification rate statistics of departments at different levelsWith year qualification rate statistics;
Step 2: according to the voltage statistic data of each monitoring point collecting, the account of the history of quality of voltage index is dividedAnalyse;
Step 2-1: the monitoring point of selecting to need analysis;
Step 2-2: select to need the quality of voltage index analyzed, quality of voltage index comprise rate of qualified voltage, voltage standard poor andVoltage probability density;
Step 2-3: select year quarterly, year monthly, season monthly or the moon analysis mode per diem, select tool according to selected analysis modeThe historical time section of body;
Step 2-4: calculate the voltage matter of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionFigureofmerit value;
Step 2-5: the quality of voltage desired value that shows selected monitoring point with the form of form, curve and excellent figure;
Step 2-6: according to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value, determine voltage matterThe monitoring point that figureofmerit is poor, reports to the police, so that electric power personnel carry out diagnostic process to the quality of voltage abnormal conditions of this monitoring point;
Step 3: according to the real-time voltage data of current each monitoring point collecting, the future trend of quality of voltage index is enteredRow on-line prediction;
Step 3-1: the monitoring point of selecting to need prediction;
Step 3-2: the quality of voltage index of selecting to need prediction;
Step 3-3: select year quarterly, year monthly, season monthly or the moon prediction mode per diem, select according to the prediction mode of selectingConcrete future time section;
Step 3-4: in the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, the electricity to disappearancePress quality index data to supplement;
Step 3-5: set up the future trend on-line prediction model of quality of voltage index, being input as from current time to certain of this modelQuality of voltage desired value in the scope during this period of time of individual historical juncture, this model is output as the electricity of the future time section that will predictPress quality index value;
Step 3-6: the quality of voltage of selected monitoring point is referred to according to the future trend on-line prediction model of the quality of voltage index of setting upTarget future trend is predicted;
Step 3-7: quality of voltage index future trend online pre-that shows selected monitoring point with the form of form, curve and excellent figureSurvey result;
Step 3-8: refer to according to the on-line prediction result of the quality of voltage index future trend of selected monitoring point, each voltage gradation qualityMark setting value, the monitoring point of definite following moment quality of voltage index error, carries out early warning, so that electric power personnel are to existing voltage matterAdvanced processing is carried out in the monitoring point of amount potential problem.
2. the voltage monitoring method of raising grid voltage quality according to claim 1, is characterized in that: in step 3-5The future trend on-line prediction model of setting up quality of voltage index carry out as follows:
Step 3-5-1: Time Created series model, time series models be input as this from current time to certain historical junctureQuality of voltage desired value in section time range, time series models are output as the quality of voltage index of the future time section that will predictValue; Time series models adopt ARIMA (p, d, q) model, wherein p, and d, q represents respectively exponent number, the difference rank of autoregression modelThe exponent number of number and moving average model(MA model);
Step 3-5-2: set up gray model, gray model be input as the model during this period of time from current time to certain historical junctureQuality of voltage desired value in enclosing, gray model output is the quality of voltage desired value of the future time section that will predict; Grey mouldType adopts GM (1,1) model;
Step 3-5-3: set up combination forecasting, the input of combination forecasting comprises the future time of time series models predictionThe quality of voltage desired value of the quality of voltage desired value of section and the future time section of Grey Model, the output of combination forecastingFor the quality of voltage desired value of future time section of time series models prediction and the voltage matter of the future time section of Grey ModelThe weighting sum of figureofmerit value, i.e. the quality of voltage desired value of the future time section of combination forecasting prediction;
Step 3-5-4: set up BP neural network model, the combination forecasting that is input as of BP neural network model is predicted notCarry out the quality of voltage desired value of time period, BP neural network model is output as the future time section of combination forecasting predictionThe error of quality of voltage desired value;
Step 3-5-5: set up the future trend on-line prediction model of quality of voltage index, the input of this model comprises combined prediction mouldThe future of the combination forecasting prediction of the quality of voltage desired value of the future time section of type prediction and the output of BP neural network modelThe error of the quality of voltage desired value of time period, on-line prediction model is output as the future time section of combination forecasting predictionThe quality of voltage index of the future time section of the combination forecasting prediction of quality of voltage desired value and the output of BP neural network modelThe error sum of value, i.e. predicting the outcome of quality of voltage index.
3. the voltage monitoring method of raising grid voltage quality according to claim 1, is characterized in that: step 2-1 instituteThe monitoring point that selection described in the monitoring point that the selection of stating need to be analyzed and step 3-1 need to be predicted include select single monitoring point,Select multiple monitoring points, once select all relevant monitoring points of circuit, once select all monitoring points of transformer station and once select countyThe all monitoring points of power supply administration.
4. the voltage monitoring method of raising grid voltage quality according to claim 1, is characterized in that: in step 2-3Described selects concrete historical time section according to selected analysis mode, and when analysis mode is year quarterly time, historical time section is selectedFor year; When analysis mode is year monthly time, historical time section is chosen as year; When analysis mode is season monthly time, historical time sectionBe chosen as time and season; When analysis mode is the moon per diem time, historical time section is chosen as time and month.
5. the voltage monitoring method of raising grid voltage quality according to claim 1, is characterized in that: in step 3-3Described select concrete future time section according to the prediction mode of selecting, when prediction mode be year quarterly time, under predicting the outcomeTime be the current year residue season; When prediction mode is year monthly time, the residue that the time under predicting the outcome is the current yearMonth; When prediction mode is season monthly time, the residue month that the time under predicting the outcome is current season; When prediction mode is the moonPer diem time, the residue number of days that the time under predicting the outcome is this month.
6. the voltage monitoring method of raising grid voltage quality according to claim 1, is characterized in that: step 3-4 instituteThe quality of voltage achievement data to disappearance of stating supplements the cubic spline interpolation method that adopts.
7. realize the grid voltage quality monitoring system of the monitoring method of raising grid voltage quality claimed in claim 1, its spyLevy and be: comprise data capture unit, historical time section quality of voltage index analysis unit, future time section quality of voltage indexPredicting unit and data storage cell;
Data capture unit is for obtaining real-time voltage data and the voltage statistic data of monitoring point;
Historical time section quality of voltage index analysis unit is used for the statistical number of each monitoring point obtaining according to data capture unitAccording to, the account of the history of quality of voltage index is analyzed, comprising: select the monitoring point of needs analysis and the voltage that needs are analyzedQuality index; Select year quarterly, year monthly, season monthly or the moon analysis mode per diem select concrete according to selected analysis modeHistorical time section; Calculate the voltage of selected monitoring point in this historical time section according to selected analysis mode and historical time sectionQuality index value; Show the quality of voltage desired value of selected monitoring point with the form of form, curve and excellent figure; According to selected monitoringThe quality of voltage desired value of point, each voltage gradation quality index set value, and determine the monitoring point of quality of voltage index error, reportAlert;
Future time section quality of voltage index prediction unit is for according to the real-time voltage data of current each monitoring point obtaining, rightThe future trend of quality of voltage index is carried out on-line prediction, comprising: select the monitoring point of needs prediction and the voltage matter of needs predictionFigureofmerit; Select year quarterly, year monthly, season monthly or the moon prediction mode per diem select concrete according to the prediction mode of selectingFuture time section; In the time there is disappearance in the quality of voltage achievement data of selected monitoring point in historical time section, to disappearanceQuality of voltage achievement data supplements; Set up the future trend on-line prediction model of quality of voltage index, being input as of this modelQuality of voltage desired value in scope during this period of time from current time to certain historical juncture, this model is output as and will predictsThe quality of voltage desired value of future time section; According to the future trend on-line prediction model of quality of voltage index of setting up to selected prisonThe future trend of the quality of voltage index of measuring point is predicted; Show the electricity of selected monitoring point with the form of form, curve and excellent figurePress the on-line prediction result of quality index future trend; According to the on-line prediction of the quality of voltage index future trend of selected monitoring pointResult, each voltage gradation quality index set value, and determine the monitoring point of future time section quality of voltage index error, carry out early warning;
Data storage cell is for becoming the future of storing the real-time voltage data of monitoring point and voltage statistic data, quality of voltage indexGesture on-line prediction model parameter, monitoring point in every quality of voltage desired value of each historical time section and monitoring point at future timeThe quality of voltage index prediction value of section.
8. grid voltage quality monitoring system according to claim 7, is characterized in that: described historical time section voltage matterIndex Analysis unit comprises that historical time section quality of voltage desired value computing module and historical time section quality of voltage index analysis showShow and alarm module;
Historical time section quality of voltage desired value computing module is for selecting to need the monitoring point of analyzing, the quality of voltage that needs analysisIndex and analysis mode, select concrete historical time section according to selected analysis mode, and then calculate selected monitoring point in this historyThe quality of voltage desired value of time period;
Historical time section quality of voltage index analysis shows and alarm module shows selected for the form with form, curve and excellent figureThe quality of voltage desired value of monitoring point; According to the quality of voltage desired value of selected monitoring point, each voltage gradation quality index setting value,Determine the monitoring point of quality of voltage index error, report to the police.
9. grid voltage quality monitoring system according to claim 7, is characterized in that: described future time section voltage matterFigureofmerit predicting unit comprise monitoring point historical data complementary module, time series models set up module, gray model set up module,Combination forecasting is set up module, BP Establishment of Neural Model module, quality of voltage index prediction module, quality of voltage and is referred toMark predicts the outcome and shows and warning module;
Monitoring point historical data complementary module is for selecting to need the monitoring point of prediction, quality of voltage index and the prediction that need to predictMode, selects concrete future time section, the voltage matter when selected monitoring point in historical time section according to the prediction mode of selectingWhen figureofmerit data exist disappearance, the quality of voltage achievement data of disappearance is supplemented;
Time series models are set up module for setting up with the voltage in the scope during this period of time from current time to certain historical junctureQuality index value is input, the time series models taking the quality of voltage desired value of the future time section that will predict as output; TimeSeries model adopts ARIMA (p, d, q) model, wherein p, and d, q represents respectively exponent number, difference order and the movement of autoregression modelThe exponent number of averaging model;
Gray model is set up module for setting up with the quality of voltage in the scope during this period of time from current time to certain historical junctureDesired value is input, gray model taking the quality of voltage desired value of the future time section that will predict as output; Gray model adoptsGM (1,1) model;
Combination forecasting set up module for setting up with the quality of voltage desired value of the future time section of time series models predictions andThe quality of voltage desired value of the future time section of Grey Model is input, with the future time section of time series models predictionsThe weighting sum of the quality of voltage desired value of the future time section of quality of voltage desired value and Grey Model is that the combination of output is pre-Survey model;
BP Establishment of Neural Model module is for setting up the quality of voltage index with the future time section of combination forecasting predictionThe error of the quality of voltage desired value of the future time section that value is predicted for input, taking combination forecasting is the BP nerve net of outputNetwork model;
Quality of voltage index prediction module for setting up with the quality of voltage desired value of the future time section of combination forecasting prediction andThe error of the quality of voltage desired value of the future time section of the combination forecasting prediction of BP neural network model output for input,With the quality of voltage desired value of future time section and the combined prediction mould of BP neural network model output of combination forecasting predictionThe error sum of the quality of voltage desired value of the future time section of type prediction is that the future trend of quality of voltage index of output is pre-onlineSurvey model, and according to the future trend on-line prediction model of quality of voltage index of setting up the quality of voltage index to selected monitoring pointFuture trend predict, obtain predicting the outcome of quality of voltage index;
Quality of voltage index prediction result shows and warning module is used for showing selected monitoring point with the form of form, curve and excellent figureThe on-line prediction result of quality of voltage index future trend, and according to the quality of voltage index future trend of selected monitoring pointLine predicts the outcome, each voltage gradation quality index setting value, determines the monitoring point of following moment quality of voltage index error, carries out pre-Alert.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410273793.4A CN104037943B (en) | 2014-06-18 | 2014-06-18 | A kind of voltage monitoring method and system that improve grid voltage quality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410273793.4A CN104037943B (en) | 2014-06-18 | 2014-06-18 | A kind of voltage monitoring method and system that improve grid voltage quality |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104037943A CN104037943A (en) | 2014-09-10 |
CN104037943B true CN104037943B (en) | 2016-05-25 |
Family
ID=51468598
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410273793.4A Active CN104037943B (en) | 2014-06-18 | 2014-06-18 | A kind of voltage monitoring method and system that improve grid voltage quality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104037943B (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104242453A (en) * | 2014-09-23 | 2014-12-24 | 北京科东电力控制系统有限责任公司 | Voltage alarm method used for buses of main electric network |
CN104376383A (en) * | 2014-11-27 | 2015-02-25 | 东北大学 | Grid voltage monitoring and prediction system and method based on geographic information system |
CN104618133B (en) * | 2014-12-18 | 2017-11-10 | 东北大学 | A kind of grid voltage quality Monitoring Data acquisition method and system |
CN104899457B (en) * | 2015-06-15 | 2017-07-25 | 西北工业大学 | Based on the satellite data Forecasting Methodology for improving unbiased GM (1,1) model |
CN105044518B (en) * | 2015-08-06 | 2018-05-22 | 江苏省电力公司苏州供电公司 | Method is determined applied to the automatic thresholding that adapts in voltage monitoring |
CN106533730B (en) * | 2015-09-15 | 2020-07-31 | 南京中兴软件有限责任公司 | Hadoop cluster component index acquisition method and device |
CN107273718A (en) * | 2017-06-27 | 2017-10-20 | 电子科技大学 | A kind of Analysis of Survival Time method of fusion dna methylation characteristic |
CN108280776A (en) * | 2018-03-27 | 2018-07-13 | 国网江西省电力有限公司信息通信分公司 | A kind of mobile electric energy internet structure and data checking method |
CN109002998A (en) * | 2018-08-01 | 2018-12-14 | 国网浙江省电力有限公司台州供电公司 | Power operation forewarning index analysis method |
CN111950918B (en) * | 2020-08-19 | 2024-04-12 | 江苏电力交易中心有限公司 | Market risk assessment method based on power transaction data |
CN112070302A (en) * | 2020-09-08 | 2020-12-11 | 北京中宸泓昌科技有限公司 | Early warning method and system for power utilization safety of power grid |
CN112258057A (en) * | 2020-10-27 | 2021-01-22 | 国网山东省电力公司昌邑市供电公司 | Analysis system capable of improving rural voltage qualification rate |
CN113629720B (en) * | 2021-08-27 | 2023-08-04 | 广东电网有限责任公司 | Full-automatic end user voltage quality improving device of distribution network |
CN113805761B (en) * | 2021-09-28 | 2022-04-15 | 中国矿业大学 | Smart power grid data analysis and visualization under support of Internet of things equipment |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235981A (en) * | 2013-04-10 | 2013-08-07 | 东南大学 | Wind power quality trend predicting method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4585472B2 (en) * | 2006-03-08 | 2010-11-24 | 中国電力株式会社 | Power quality monitoring device |
-
2014
- 2014-06-18 CN CN201410273793.4A patent/CN104037943B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235981A (en) * | 2013-04-10 | 2013-08-07 | 东南大学 | Wind power quality trend predicting method |
Non-Patent Citations (1)
Title |
---|
"基于GIS的电压质量监控系统的设计与开发";徐泉等;《控制工程》;20130131;第20卷(第1期);第192-196页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104037943A (en) | 2014-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104037943B (en) | A kind of voltage monitoring method and system that improve grid voltage quality | |
CN109783916B (en) | Air compressor group optimal scheduling decision method based on simulation technology | |
He et al. | Forecasting China's total energy demand and its structure using ADL-MIDAS model | |
CN103400209B (en) | Power distribution network maintenance embodiment optimization method | |
Xiao et al. | A hybrid model based on data preprocessing for electrical power forecasting | |
CN102722759B (en) | Method for predicting power supply reliability of power grid based on BP neural network | |
CN106779277B (en) | Classified evaluation method and device for network loss of power distribution network | |
CN103617371A (en) | Method for comprehensively evaluating electric energy quality based on grey theory | |
CN103761690A (en) | Evaluation method based on voltage reactive power control system in grid system | |
CN105913175A (en) | Intelligent power grid short period load prediction method based on improved nerve network algorithm | |
CN103996147A (en) | Comprehensive evaluation method for power distribution network | |
CN110490409B (en) | DNN-based low-voltage transformer area line loss rate benchmarking value setting method | |
CN104933629A (en) | Power user equipment evaluation method based on interval level analysis and interval entropy combination | |
CN103985000A (en) | Medium-and-long term typical daily load curve prediction method based on function type nonparametric regression | |
CN104573857A (en) | Power grid load rate prediction method based on intelligent algorithm optimization and combination | |
CN103530700B (en) | Urban distribution network saturation loading Comprehensive Prediction Method | |
CN110059913A (en) | A kind of quantitative estimation method counted and the power failure of future-state is planned | |
CN105225021A (en) | The optimum choice method of power distribution network project yet to be built | |
CN110110921A (en) | A kind of river level prediction technique considering time-lag effect | |
CN107368940A (en) | Count and respond uncertain temperature control Load aggregation response potential evaluation method and system | |
CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
Yılmaz | Real measure of a transmission line data with load fore-cast model for the future | |
CN104218571A (en) | Running state evaluation method for wind power generation equipment | |
CN116757544A (en) | Comprehensive evaluation method and system for power quality additional loss of power distribution network | |
CN103208036B (en) | A kind of short-term load forecasting method of electrically-based user data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |