CN105811402B - A kind of Electric Load Prediction System and its Forecasting Methodology - Google Patents
A kind of Electric Load Prediction System and its Forecasting Methodology Download PDFInfo
- Publication number
- CN105811402B CN105811402B CN201610163622.5A CN201610163622A CN105811402B CN 105811402 B CN105811402 B CN 105811402B CN 201610163622 A CN201610163622 A CN 201610163622A CN 105811402 B CN105811402 B CN 105811402B
- Authority
- CN
- China
- Prior art keywords
- power
- mrow
- load
- electric
- msub
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000009826 distribution Methods 0.000 claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 238000007726 management method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000001131 transforming effect Effects 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000005611 electricity Effects 0.000 claims description 74
- 230000008859 change Effects 0.000 claims description 31
- 238000004891 communication Methods 0.000 claims description 26
- 230000001932 seasonal effect Effects 0.000 claims description 23
- 238000012417 linear regression Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 11
- 241000196324 Embryophyta Species 0.000 claims description 10
- 240000002853 Nelumbo nucifera Species 0.000 claims description 8
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 8
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 238000005265 energy consumption Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013523 data management Methods 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 244000131316 Panax pseudoginseng Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 11
- 238000012271 agricultural production Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 241001269238 Data Species 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 238000003869 coulometry Methods 0.000 description 3
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010224 classification analysis Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004454 trace mineral analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0073—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source when the main path fails, e.g. transformers, busbars
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention belongs to power system electric energy data processing technology field,More particularly to a kind of Electric Load Prediction System and its Forecasting Methodology,Including electric power load control unit,Electric energy acquisition unit,Distribution network automated service unit,Electric power marketing MIS service unit,Transforming plant protecting center cell and power-management centre service unit,The electric power load control unit respectively with electric energy acquisition unit,Distribution network automated service unit,Electric power marketing MIS service unit,Transforming plant protecting center cell and power-management centre service unit are attached,The Forecasting Methodology of the present invention is the collection power consumer information in units of power network line title,Tracking and inquiry,Carry out line load and calculate analyzing and processing,Obtain every circuit short-term load forecasting curve of power distribution network and take the every prediction index for influenceing electric load,The present invention can be to moving reason retrospect and external factor impact evaluation analysis with electric load field wave,Realize the monitoring of electric power power consumption and prediction.
Description
Technical field
The invention belongs to power system electric energy data analysis technical field, more particularly to a kind of Electric Load Prediction System
And its Forecasting Methodology.
Background technology
Substantial amounts of marketing, metering, operation of power networks data producing level be not high.With the continuous hair of computer information technology
Open up, substantial amounts of number is have accumulated in all kinds of operation systems (Marketing Management Information System, metering automation system, scheduling EMS system)
According to resource, system can gather and store a large amount of client's information about power, including client properties, client's load characteristic, electricity feature etc.,
It can not effectively be applied, cause the waste of data resource.The Electricity market analysis to become more meticulous is one
Unite engineering, involved data volume is very huge, the intelligent means of Electricity market analysis deficiency, human factor influence compared with
It is more.Effective conclusion only can not be obtained by simply calculating with Market Analyst, and its subjectivity will be to a certain degree
On have influence on the accuracy of market analysis.If because post personnel change, due to laggard employee experience accumulation in a short time not
Foot, can cause the reasonable science of forecast analysis can not be continuous.The complicated economic situation of our times largely increases
Judgement difficulty to Power Market Development rule, the change an urgent demand Utilities Electric Co. of economic situation understand power sales in depth
Endogenous development change mechanism, and its influence factor and regularity are sought, provide scientific basis for scientific forecasting market future trend.
Electrical Market Forecasting analysis at present lays particular emphasis on overall macroscopic analysis, lacks the analysis to microcosmic market.With market
Form constantly produces new change, it is necessary to improve the degree that becomes more meticulous of market analysis, there is provided market internal and external reasonses analysis of Influential Factors,
Demand response, electrity market activity tracking, monitoring etc. microcosmic market refinement analytic function, market analysis forecast work often according to
Rely power system internal data, have ignored the trace analysis influenceed on external environment.The development of electricity market is by a variety of external
The influence of environment, it is economical whether prosperous largely to influence electric power for the larger region of industrial proportion
Market development running orbit.Analysis for external economy environment in the past often based on ex-post analysis, can not be instructed not send a telegram here
Power develops, and therefore, grid company can clearly cause the major influence factors of turn of the market, therefrom excavate influence electricity market
Main industries, main users and the reason of change, accurately hold user, the fluctuation of industry quantity of electricity is fluctuated with regional quantity of electricity
Between contact, consider its influence to power network for user and decision-making foundation be provided.
The content of the invention
The purpose of the present invention is the above mentioned problem for solving prior art, there is provided a kind of Electric Load Prediction System and its prediction
Method, the present invention collection tracking in real time can be carried out to electric load and power structure solution is analyzed, and judges that electric load fluctuates
It is monitored and statistical analysis, realizes the monitoring of electric load, to achieve these goals, the technical solution adopted by the present invention is such as
Under：
A kind of Electric Load Prediction System, it is characterised in that：Including electric power load control unit, electric energy acquisition unit, match somebody with somebody
Grid automation service unit, Electric power marketing MIS service unit, transforming plant protecting center cell and power-management centre service are single
Member, the electric power load control unit respectively with electric energy acquisition unit, distribution automation system service unit, power marketing
MIS service units, transforming plant protecting center cell and power-management centre service unit are attached, the electric power load control
Unit obtains and calculated respectively power transmission parameter, the transforming plant protecting center list that analyzing and processing electric energy acquisition unit gathers from power network
What member output quality of power supply energy consumption parameter, distribution automation system took unit output matches somebody with somebody electrical parameter data, and is power marketing
MIS service units provide information on load, and carry out conveying to power-management centre service unit and realize that fault location, diagnosis are reported
Accuse, and realize the reports such as Fault Isolation, load transfer, field failure maintenance, the power load of the Electric power marketing MIS service unit
Lotus prediction result is transmitted into power-management centre service unit by electric power load control unit is scheduled distribution, the electricity
Power marketing MIS service units include electricity consumption subscriber information management module, electric load tracking module, electric power power structure analysis mould
Block, electric load early warning module and electric load decision-making module, the electricity consumption subscriber information management module pass sequentially through power load
Lotus tracking module, electric power power structure analysis module, electric load early warning module connect with electric load decision-making module.
Preferably, the electric power load control unit connects including embedded Communication processor, network interface card extending controller, UART
Mouth circuit, SDRAM memory, clock reference circuit, COM communication controlers, flash storage, LCD display, CAN interface electricity
Road and ethernet interface, it is described state embedded Communication processor respectively with ethernet interface, UART interface circuit,
SDRAM memory, clock reference circuit, CAN interface circuit, COM communication controlers, flash storage and network interface card extension control
Device is connected, and the network interface card extending controller is connected with distribution network automated service unit, the ethernet interface and electric power
MIS service units of marketing are connected, and the UART interface circuit is connected with LCD display, the CAN interface circuit and electric energy acquisition
Unit connects.
Preferably, the embedded Communication processor by pci bus and network interface card extending controller, flash storage,
COM communication controlers are communicated to connect, and the embedded Communication processor is connected by EX buses with CAN interface circuit communication.
Preferably, the distribution automation system takes unit and is used for historical data management, decision implement data acquisition, prison
Depending on control, fault location and alarm, sequence of events recording, statistics calculating and the drafting of electric load curve, including at least SCADA
Module, distribution geography information module and dsm module.
A kind of Methods of electric load forecasting, it is characterised in that：Comprise the following steps：
Step 1：Power consumer information is collected in units of power network line title, and electricity substantially is obtained from distribution network line
Parameter is measured, establishes grid power circuit power load information database, the power consumer information of collection is stored in electricity consumption user letter
Cease management module；It is to industry-by-industry classification, sale of electricity classification, spy to whole electricity market power consumer information and classification
Determine customer group, specify user to be collected classification analysis, it mainly includes load curve and typical curve and coulometric analysis etc.；
Step 2：Electric load tracking module can be to power load according to the user power utilization amount historical data on distribution network line
The unusual action information factor that lotus impacts is monitored, and the factor impacted to electric load information is carried out at seasonal adjustment
Reason, to obtain the every prediction index for influenceing electric load；
Step 3：Electric load decision-making module is screened by linear regression model (LRM) to each prediction index, power consumer
Power information is tracked and inquired about, and rejects the influence of distribution network line load factor and calendar effect, carries out line load meter
Analyzing and processing is calculated, the optimal trend of electric load change is obtained, every circuit short-term load forecasting curve of power distribution network is obtained, to electricity
Power distribution network line electricity market in each season in predetermined period is planned and predicted.
Preferably, the seasonal adjustment processing carries out structure change stabilization by X-12-ARIMA seasonal adjustment methods
Prediction index data, in order to analyze the feature of electrity market seasonal move and correct estimation and reflect the basic of season power consumption
Development trend.Sequence after working process can reflect every profession and trade power consumption Secular Variation Tendency and fluctuating range；
The X-12-ARIMA seasonal adjustment methods model calculation expression is：
In formula (61), ytTrade power consumption amount is represented, λ=1 has corresponded to linear transformation, and λ=0 has corresponded to logarithmic transformation, remaining
Smooth variation occurs with λ for conversion, such as in general economic indicator sequence, dtNumber Sequence, Y are removed for onetRepresent actual electricity consumption
Amount.
Preferably, the linear regression model (LRM) calculation expression is：
In formula (71), ytTrade power consumption amount is represented, x represents Industrial Cycle index, and r represents the lag period, and c represents constant term, t
Represent time, ztRepresent stochastic error.
In summary, the present invention has following remarkable result as a result of above technical scheme, the present invention：
(1), the present invention fully judges the state of development of power load, by the analysis to historical development rule and to present situation
Assurance, in time find the leading power consumption index of market development, and on caused by the power load influence give rationally to assess.
(2), the present invention can carry out collection tracking in real time to electric power electricity consumption and power structure solution be analyzed, to power load
The cause of fluctuation retrospect of lotus field and external factor impact evaluation analysis, realize the monitoring of electric power power consumption and prediction.
(3), the present invention can in time, comprehensively monitor the fluctuating change situation of power consumption/load, ensure that power equipment is long-term
Reliable and stable operation is each electric power power consumption/Power system load data to provide strong, finer support, is electric power
Load prediction and monitoring, the continuous data of various kinds of equipment power consumption is transmitted to realize, and save a large amount of human costs and circuit
The engineerings such as transformation are into providing decision support
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of present example or technical scheme of the prior art
There is the accompanying drawing required in technology description to do simply to introduce, it should be apparent that, drawings in the following description are only the present invention
Some examples, to those skilled in the art, can also be attached according to these on the premise of creativeness is not paid
Figure obtains other accompanying drawings.
Fig. 1 is a kind of schematic diagram of Electric Load Prediction System of the present invention.
Fig. 2 is a kind of electric power load control unit schematic diagram of Electric Load Prediction System of the present invention.
Fig. 3 is a kind of Analysis And Computation Division reason flow chart of Methods of electric load forecasting of the present invention.
Fig. 4 is a kind of schematic diagram of the Electric power marketing MIS service unit of Electric Load Prediction System of the present invention.
Fig. 5 is a kind of present invention non-general industrial user in January, 2010 of Methods of electric load forecasting in December, 2014 reality
Border power consumption curve map.
Fig. 6 is that a kind of non-general industrial user X-12-ARIMA seasonal adjustments program of Methods of electric load forecasting of the present invention is adjusted
Electricity needs progress curve figure after whole.
Fig. 7 is a kind of actual use present invention commercial user's in January, 2010 in December, 2014 of Methods of electric load forecasting
Electric quantity curve figure.
Fig. 8 is after a kind of commercial user's X-12-ARIMA seasonal adjustments program of Methods of electric load forecasting of the present invention adjusts
Electricity needs progress curve figure,
Fig. 9 is a kind of actual use present invention agricultural production in January, 2010 in December, 2014 of Methods of electric load forecasting
Electric quantity curve figure.
Figure 10 is a kind of agricultural production X-12-ARIMA seasonal adjustments program adjustment of Methods of electric load forecasting of the present invention
Electricity needs progress curve figure afterwards.
Embodiment
Below in conjunction with the accompanying drawing in present example, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Based on hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
1 and Fig. 2 below in conjunction with the accompanying drawings, a kind of Electric Load Prediction System, including electric power load control unit, electric energy acquisition
In unit, distribution network automated service unit, Electric power marketing MIS service unit, transforming plant protecting center cell and power scheduling
Central server unit, the electric power load control unit respectively with electric energy acquisition unit, distribution automation system service unit, electricity
Power marketing MIS service units, transforming plant protecting center cell and power-management centre service unit are attached, the power load
Lotus control unit obtains and calculated respectively power transmission parameter, the transforming plant protecting that analyzing and processing electric energy acquisition unit gathers from power network
Center cell output quality of power supply energy consumption parameter, distribution automation system take the electrical parameter data of matching somebody with somebody of unit output, and are electricity
Power marketing MIS service units provide information on load, and to power-management centre service unit carry out conveying realize fault location,
Diagnosis report, and the reports such as Fault Isolation, load transfer, field failure maintenance are realized, the Electric power marketing MIS service unit
Load forecast result is transmitted into power-management centre service unit by electric power load control unit and is scheduled distribution；
The distribution automation system takes unit and is used for historical data management, decision implement data acquisition, monitoring control, fault location
With alarm, sequence of events recording, statistics calculating and the drafting of electric load curve, believe including at least SCADA modules, distribution geography
Cease module (GIS) and dsm module (DSM).The Electric power marketing MIS service unit includes electricity consumption subscriber information management
Module, electric load tracking module, electric power power structure analysis module, electric load early warning module and electric load decision model
Block, the electricity consumption subscriber information management module pass sequentially through electric load tracking module, electric power power structure analysis module, electric power
Load warning module connects with electric load decision-making module.
In embodiments of the present invention, as shown in figure 3, the electric power load control unit include embedded Communication processor,
Network interface card extending controller, UART interface circuit, SDRAM memory, clock reference circuit, COM communication controlers, Flash storages
Device, LCD display, CAN interface circuit and ethernet interface, it is described state embedded Communication processor respectively with ether Netcom
Believe interface, UART interface circuit, SDRAM memory, clock reference circuit, CAN interface circuit, COM communication controlers, Flash
Memory is connected with network interface card extending controller, and the network interface card extending controller is connected with distribution network automated service unit, described
Ethernet interface is connected with Electric power marketing MIS service unit, and the UART interface circuit is connected with LCD display, described
CAN interface circuit is connected with electric energy acquisition unit.The embedded Communication processor is controlled by pci bus and network interface card extension
Device, flash storage, the communication connection of COM communication controlers, the embedded Communication processor pass through EX buses and CAN interface
Circuit communication connects.
In the present invention, the electric energy acquisition unit includes current sensor, voltage sensor or intelligence electricity as shown in Figure 3
Table, electric energy acquisition unit obtains the parameter signals such as accurate voltage electric current from power network and sent to embedded Communication processor, from power network
Obtaining the parameters such as accurate voltage electric current includes basic electrical parameter, harmonic voltage electric current, frequency and voltage deviation, imbalance and sequence
The parameters such as component, voltage pulsation and flickering, send embedded Communication processor and calculated and analyzed and processed to obtain the negative of power network
The data such as lotus curve, voltage, electric current, frequency, power, DC component, harmonic detecting, dead electricity detection, dead electricity power recording.It is described
The parameter of transforming plant protecting center cell output includes transmission line equipment parameter, transformer equipment parameter, power capacitor ginseng
The parameters such as number, asynchronous machine are used to calculate quality of power supply energy consumption data.The distribution automation system server is based on SCADA
System, distribution GIS-Geographic Information System (GIS) and dsm (DSM), according to voltage, power factor, the electricity for obtaining power distribution network
The parameters such as stream are implemented data acquisition, monitoring control, fault location and alarm, sequence of events recording and statistics and calculated, and then pass through
Electric power load control unit carries out conveying to power-management centre service unit and realizes fault location, diagnosis report, and realizes event
Phragma is from reports such as the transfer of, load, field failure maintenance.The electric energy acquisition unit, distribution network automated service is single and member becomes
The data of power station protection center cell are conveyed into electric power load control unit and carry out calculating processing, single for Electric power marketing MIS service
Member provides a variety of electricity/information on loads, and the data that electric power load control unit calculate processing include 3 seconds real time datas, 3
Minute statistical value and different interval statistical value；Wherein, different interval statistical value includes day statistical interval value, all statistical intervals, the moon
Statistical interval value, power consumption/load of season statistical interval value and year statistical interval value, year-on-year rate of change, ring are than rate of change etc.
Graphic analyses, by the data storage for calculating processing in local flash storage, these power information datas of storage can be led to
Cross ethernet interface and transmit to Electric power marketing MIS service unit and analyzed and processed., can by these energy consumption datas of storage
The power information data of acquisition is analyzed and processed with being transmitted by ethernet interface to Electric power marketing MIS service unit
And load prediction, then taken again by being transmitted by ethernet interface, electric power load control unit to power-management centre
Business unit carries out power scheduling and distribution.
As shown in figure 4, the Electric power marketing MIS service unit include electricity consumption subscriber information management module, electric load with
Track module, electric power power structure analysis module, electric load early warning module and electric load decision-making module, the electricity consumption user letter
Breath management module passes sequentially through electric load tracking module, electric power power structure analysis module, electric load early warning module and electricity
Power load decision-making module connects.The electricity consumption subscriber information management module carries out electricity price/electricity bill control, load management to each user
Etc. the operation work of business, and relevant user geographical position is inquired about, automatically generate various power supply plans.Power department staff
Analysis is predicted to whole electric power power consumption/load by Electric power marketing MIS service unit, first, to power consumer information
It is managed, quantitative statisticses and analyzes prediction, and ensures data source integrality and accuracy, secondly, electric load tracking mould
Block is used for the influence factor of electric power variation fluctuation and electric power power consumption/load data is tracked and inquired about, and slaps exactly
The major influence factors of electric load change are held, electric power power structure analysis module is used to analyze fluctuating, being external for electricity/load
Factor fluctuates and power structure (regional electricity/electric structure parsing and industry electricity/load configuration parsing, by various correlations
Factor influences such as influence of meteorology, mineral products, factory of enterprise, agricultural production, residential electricity consumption, power plant for self-supply's factor to load),
The electric load early warning module provides intelligentized electric load early warning and the change to electric load carried out automatic, regular
Monitoring, to obtain the every prediction index for influenceing electric load, prediction index includes load curve, minimum load, maximum load,
Average load；Once it was found that there is anomalous variation to send alarm, to relevant staff to prompt.The electric load decision model
Block is used to carry out analysis judgement to whole electric load early warning, fluctuating characteristic, generation prediction electric load market trend
Report, proposes that corresponding prediction scheme provides flexible, effective electric power power consumption/load Analysis and prediction for power department.
With reference to shown in Fig. 1, Fig. 2, Fig. 3 and Fig. 4, a kind of Methods of electric load forecasting, comprise the following steps：
Step 1：Power consumer information is collected in units of power network line title, and electricity substantially is obtained from distribution network line
Parameter is measured, establishes grid power circuit power load information database, and obtained from electric energy acquisition unit with power network line
Title is that unit collects power consumer information, and the power consumer information of collection is stored in into electricity consumption subscriber information management module, and right
Whole electricity market power consumer information and classification be to industry-by-industry classification, sale of electricity classification, particular group, specify
User is collected classification analysis, and it mainly includes load curve and typical curve and coulometric analysis etc., and coulometric analysis is to each
Individual category of employment, sale of electricity classification, particular group, specified user are analyzed.Day, the moon, season, year etc. different time latitude enter
Row electricity, year-on-year rate of change, ring divide than the chart of rate of change etc., and proportion, growth rate, contrast, history ring ratio, client over the years
Ranking etc..
Wherein, load curve includes with typical curve：
(a), using day as time dimension, Macro or mass analysis different industries classification, sale of electricity classification, particular group, specified user
Daily load curve.
(b) to analyze typical load curve as time dimension in the moon, season.
Step 2：Electric load tracking mould can be to electric load according to the user power utilization amount historical data on distribution network line
The unusual action information factor impacted is monitored, and the factor impacted to electric load information is carried out at seasonal adjustment
Reason, to obtain the every prediction index for influenceing electric load；Electric load tracking module in the present invention is to electric power variation ripple
Dynamic influence factor and electric power power consumption/load data is tracked and inquired about, and the change to electric load carry out from
The factor that dynamic, periodic monitoring, electric load information impact carries out seasonal adjustment processing, influences electric load to obtain
Every prediction index；The major influence factors of electric load change are grasped exactly, and electric power power structure analysis module is used to divide
Analyse fluctuation, external factor fluctuation and power structure (regional electricity/electric structure parsing and the industry electricity/load of electricity/load
Structure elucidation, influenceed by various correlative factors such as meteorology, mineral products, factory of enterprise, agricultural production, residential electricity consumption, provide electricity for oneself
Influence of the factors such as factory to load).
Step 3：Electric load decision-making module is screened by linear regression model (LRM) to each prediction index, power consumer
Power information is tracked and inquired about, and rejects the influence of distribution network line load factor and calendar effect, carries out line load meter
Analyzing and processing is calculated, the optimal trend of electric load change is obtained, every circuit short-term load forecasting curve of power distribution network is obtained, to electricity
Power distribution network line electricity market in each season in predetermined period is planned and predicted；In order to analyze electrity market season
The feature of variation and the basic trend of correct estimation and reflection season power consumption.Electric load decision model in the present invention
Block is used to carry out analysis judgement to whole electric load early warning, fluctuating characteristic, by linear regression model (LRM) to each prediction index
Screened, generation prediction electric load market trend report, propose that corresponding prediction scheme provides spirit for power department
Living, effective electric power power consumption/load Analysis and prediction.
As highly preferred embodiment of the present invention, the seasonal adjustment processing is entered by X-12-ARIMA seasonal adjustment methods
The stable prediction index data of row structure change, the sequence after working process can reflect every profession and trade power consumption change in long term
Trend and fluctuating range；The X-12-ARIMA seasonal adjustment methods model calculation expression is：
In formula (61), ytTrade power consumption amount is represented, λ=1 has corresponded to linear transformation, and λ=0 has corresponded to logarithmic transformation, remaining
Smooth variation occurs with λ for conversion, such as in general economic indicator sequence, dtNumber Sequence, Y are removed for onetRepresent actual electricity consumption
Amount.
It is described to remove Number Sequence dtMeet symmetrical change：Symmetrical rate of change C is asked to it firsti(t)：
Ci(t)=200 × [di(t)-di(t-1)]/[di(t)+di(t-1)] (62)；
In formula (62), when composing indexes take 0 or negative value, or when Index Content is ratio, then when taking the index adjacent
The difference at quarter, that is, meet：
Ci(t)=di(t)-di(t-1) (63)；
C in formula (63)i(t)、di(t) it is respectively value of i-th of index at the moment.
In embodiments of the present invention, screening is carried out to each prediction index by linear regression and removes exceptional value and calendar effect
Answer, obtain the optimal trend of the change of electric load, the linear regression model (LRM) calculation expression is：
In formula (71), ytTrade power consumption amount is represented, x represents Industrial Cycle index, and r represents the lag period, and c represents constant term, t
Represent time, ztRepresent stochastic error.
The present invention by taking 2010-2014 Guangxi province main industries electricity consumption initial data as an example, to it is non-it is general industry, business,
The electricity consumption of resident living and agricultural production carries out period forecasting, and the data gathered are as shown in table 1, the electricity consumption to being gathered
The data that data are carried out after seasonal periodicity adjustment are as shown in table 2.
Table 1：2010-2014 Guangxi province main industries electricity consumption initial data (units：Hundred million kilowatt hours)
Table 2：Data (unit after Guangxi province main industries electricity consumption seasonal adjustment in 2010-2014：Hundred million kilowatt hours)
Fig. 5 be non-general industrial user in January, 2010 in December, 2014 actual power consumption, Fig. 6 is non-general industrial user X-
Electricity needs progress curve after the adjustment of 12-ARIMA seasonal adjustments program, comparison diagram 5 and Fig. 6 be to 2010-2014 I,
IIth, III, IV is predicted processing season, as we know from the figure the optimal trend of electric load change, can according to change curve
Carry out the trend of the electricity needs development of load prediction.
Fig. 7 be commercial user in January, 2010 in December, 2014 actual power consumption, Fig. 8 is commercial user X-12-ARIMA
Electricity needs progress curve after the adjustment of seasonal adjustment program, comparison diagram 7 and Fig. 8 be to 2010-2014 I, II, III, IV
Four seasons was predicted processing, as we know from the figure the optimal trend of electric load seasonal periodicity change, according to change curve
The trend of the electricity needs development of load prediction can be carried out.
Fig. 9 is agricultural production in January, 2010 in December, 2014 actual power consumption, Figure 10 agricultural production X-12-ARIMA seasons
Save the electricity needs progress curve after adjustment programme adjustment, comparison diagram 9 and Figure 10 be to 2010-2014 I, II, III, IV
Four seasons was predicted processing, as we know from the figure the optimal trend of electric load seasonal periodicity change, according to change curve
The trend of the electricity needs development of load prediction can be carried out.
The preferred embodiment of invention is the foregoing is only, is not intended to limit the invention, all spirit in the present invention
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (7)
- A kind of 1. Electric Load Prediction System, it is characterised in that：Including electric power load control unit, electric energy acquisition unit, distribution Automation service unit, Electric power marketing MIS service unit, transforming plant protecting center cell and power-management centre service are single Member, the electric power load control unit respectively with electric energy acquisition unit, distribution automation system service unit, power marketing MIS service units, transforming plant protecting center cell and power-management centre service unit are attached, the electric power load control Unit obtains and calculated respectively power transmission parameter, the transforming plant protecting center list that analyzing and processing electric energy acquisition unit gathers from power network What member output quality of power supply energy consumption parameter, distribution automation system took unit output matches somebody with somebody electrical parameter data, and is power marketing MIS service units provide information on load, and carry out conveying to power-management centre service unit and realize that fault location, diagnosis are reported Accuse, and realize the reports such as Fault Isolation, load transfer, field failure maintenance, the power load of the Electric power marketing MIS service unit Lotus prediction result is transmitted into power-management centre service unit by electric power load control unit is scheduled distribution, the electricity Power marketing MIS service units include electricity consumption subscriber information management module, electric load tracking module, electric power power structure analysis mould Block, electric load early warning module and electric load decision-making module, the electricity consumption subscriber information management module pass sequentially through power load Lotus tracking module, electric power power structure analysis module, electric load early warning module connect with electric load decision-making module.
- A kind of 2. Electric Load Prediction System according to claim 1, it is characterised in that：The electric power load control unit Including embedded Communication processor, network interface card extending controller, UART interface circuit, SDRAM memory, clock reference circuit, COM Communication controler, flash storage, LCD display, CAN interface circuit and ethernet interface, the embedded mailing address Manage device respectively with ethernet interface, UART interface circuit, SDRAM memory, clock reference circuit, CAN interface circuit, COM communication controlers, flash storage connect with network interface card extending controller, and the network interface card extending controller and power distribution network are automatic Change service unit connection, the ethernet interface is connected with Electric power marketing MIS service unit, the UART interface circuit and LCD display is connected, and the CAN interface circuit is connected with electric energy acquisition unit.
- A kind of 3. Electric Load Prediction System according to claim 2, it is characterised in that：The embedded Communication processor Communicated to connect by pci bus and network interface card extending controller, flash storage, COM communication controlers, the embedded communication Processor is connected by EX buses with CAN interface circuit communication.
- A kind of 4. Electric Load Prediction System according to claim 1, it is characterised in that：The distribution automation system Take unit and be used for historical data management, decision implement data acquisition, monitoring control, fault location and alarm, sequence of events recording, Statistics calculates and the drafting of electric load curve, including at least SCADA modules, distribution geography information module and dsm mould Block.
- A kind of 5. Methods of electric load forecasting, it is characterised in that：Comprise the following steps：Step 1：Power consumer information is collected in units of power network line title, and basic electricity ginseng is obtained from distribution network line Number, establishes grid power circuit power load information database, and the power consumer information of collection is stored in into electricity consumption user profile pipe Manage module；Step 2：Electric load tracking module can be made according to the user power utilization amount historical data on distribution network line to electric load Unusual action information factor into influence is monitored, and the factor impacted to electric load information carries out seasonal adjustment processing, To obtain the every prediction index for influenceing electric load；Step 3：Electric load decision-making module is screened by linear regression model (LRM) to each prediction index, the electricity consumption of power consumer Information is tracked and inquired about, and rejects the influence of distribution network line load factor and calendar effect, carries out line load calculating point Analysis is handled, and is obtained the optimal trend of electric load change, is obtained every circuit short-term load forecasting curve of power distribution network, electric power is matched somebody with somebody Power network line electricity market in each season in predetermined period is planned and predicted.
- A kind of 6. Methods of electric load forecasting according to claim 5, it is characterised in that：The seasonal adjustment processing is logical Cross X-12-ARIMA seasonal adjustment methods and carry out the stable prediction index data of structure change, the X-12-ARIMA seasonal adjustments Method model calculation expression meets：<mrow> <msubsup> <mi>y</mi> <mi>t</mi> <mrow> <mo>(</mo> <mi>&lambda;</mi> <mo>)</mo> </mrow> </msubsup> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Y</mi> <mi>t</mi> </msub> <mo>/</mo> <msub> <mi>d</mi> <mi>t</mi> </msub> </mrow> </mtd> <mtd> <mrow> <mi>&lambda;</mi> <mo>=</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msup> <mi>&lambda;</mi> <mn>2</mn> </msup> <mo>+</mo> <mo>&lsqb;</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>Y</mi> <mi>t</mi> </msub> <mo>/</mo> <msub> <mi>d</mi> <mi>t</mi> </msub> <mo>)</mo> </mrow> <mi>&lambda;</mi> </msup> <mo>-</mo> <mn>1</mn> <mo>&rsqb;</mo> <mo>/</mo> <mi>&lambda;</mi> </mrow> </mtd> <mtd> <mrow> <mi>&lambda;</mi> <mo>&NotEqual;</mo> <mn>0</mn> <mo>,</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>l</mi> <mi>o</mi> <mi>g</mi> <mrow> <mo>(</mo> <msub> <mi>Y</mi> <mi>t</mi> </msub> <mo>/</mo> <msub> <mi>d</mi> <mi>t</mi> </msub> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <mi>&lambda;</mi> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>61</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>In formula (61), ytRepresent trade power consumption amount, λ=1 corresponded to linear transformation, and λ=0 has corresponded to logarithmic transformation, remaining conversion with Smooth variation, d occur for λtNumber Sequence, Y are removed for onetRepresent actual power consumption.
- A kind of 7. Methods of electric load forecasting according to claim 5, it is characterised in that：The linear regression model (LRM) calculates Expression formula is：<mrow> <msub> <mi>y</mi> <mi>t</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>m</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>r</mi> </munderover> <msub> <mi>&alpha;</mi> <mi>m</mi> </msub> <msub> <mi>y</mi> <mrow> <mi>t</mi> <mo>-</mo> <mi>m</mi> </mrow> </msub> <mo>+</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>n</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>r</mi> </munderover> <msub> <mi>&beta;</mi> <mi>n</mi> </msub> <msub> <mi>x</mi> <mrow> <mi>t</mi> <mo>-</mo> <mi>m</mi> </mrow> </msub> <mo>+</mo> <mi>c</mi> <mo>+</mo> <msub> <mi>z</mi> <mi>t</mi> </msub> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>71</mn> <mo>)</mo> </mrow> <mo>;</mo> </mrow>In formula (71), ytTrade power consumption amount is represented, x represents Industrial Cycle index, and r represents the lag period, and c represents constant term, and t is represented Time, ztRepresent stochastic error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610163622.5A CN105811402B (en) | 2016-03-22 | 2016-03-22 | A kind of Electric Load Prediction System and its Forecasting Methodology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610163622.5A CN105811402B (en) | 2016-03-22 | 2016-03-22 | A kind of Electric Load Prediction System and its Forecasting Methodology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105811402A CN105811402A (en) | 2016-07-27 |
| CN105811402B true CN105811402B (en) | 2018-03-06 |
Family
ID=56453574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610163622.5A Active CN105811402B (en) | 2016-03-22 | 2016-03-22 | A kind of Electric Load Prediction System and its Forecasting Methodology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105811402B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106786539A (en) * | 2016-12-30 | 2017-05-31 | 江苏金风科技有限公司 | Load data harvester, prediction control device and load monitoring system |
| CN107067343A (en) * | 2017-04-17 | 2017-08-18 | 国网浙江省电力公司经济技术研究院 | A kind of sale of electricity side operating service management platform based on the marketization |
| CN107634515A (en) * | 2017-08-22 | 2018-01-26 | 国网浙江新昌县供电公司 | Optimal operation model of tea area based on analysis of power consumption characteristics in tea area |
| CN107527121A (en) * | 2017-09-18 | 2017-12-29 | 云南电网有限责任公司信息中心 | A kind of method of the information system running status diagnosis prediction of power network |
| CN109459659A (en) * | 2018-11-14 | 2019-03-12 | 国网黑龙江省电力有限公司信息通信公司 | It is a kind of for predicting the system and method for electric power system fault |
| CN109782709A (en) * | 2018-12-29 | 2019-05-21 | 北京航天福道高技术股份有限公司 | A kind of data acquisition monitoring system applied to military enterprise |
| JP7156975B2 (en) | 2019-02-26 | 2022-10-19 | 三菱重工業株式会社 | Management evaluation device, management evaluation method, and program |
| CN110275052B (en) * | 2019-04-26 | 2022-04-15 | 国网浙江省电力有限公司衢州供电公司 | Intelligent electric energy meter for short-term prediction of user power consumption |
| CN110705232B (en) * | 2019-08-27 | 2023-04-07 | 国网山东省电力公司信息通信公司 | Method and system for generating service state analysis report of power communication network maintenance influence |
| CN111314162A (en) * | 2019-11-29 | 2020-06-19 | 中国电力科学研究院有限公司 | A method and system for drive test of power service based on drive tester |
| CN112116265B (en) * | 2020-09-25 | 2025-03-07 | 国网上海市电力公司 | A method for constructing industry prosperity index driven by power data |
| CN112232559B (en) * | 2020-10-12 | 2023-06-13 | 国网江西省电力有限公司信息通信分公司 | A short-term forecasting method and device for power regional load |
| CN112448477A (en) * | 2020-11-03 | 2021-03-05 | 南京鼎臻自动化科技有限公司 | Intelligent monitoring power distribution control system based on Internet of things |
| CN113283679A (en) * | 2021-06-30 | 2021-08-20 | 南京理工大学 | AI artificial intelligence based power load prediction system |
| CN113935519A (en) * | 2021-09-16 | 2022-01-14 | 南方电网数字电网研究院有限公司 | An AI-based network source load forecasting data management system |
| CN114172265A (en) * | 2021-11-23 | 2022-03-11 | 保定市冀能电力自动化设备有限公司 | Comprehensive protection measurement and control system |
| CN114881254A (en) * | 2022-03-17 | 2022-08-09 | 广西电网有限责任公司贵港供电局 | Electricity Marketing Self-Service System |
| CN115062869B (en) * | 2022-08-04 | 2022-12-09 | 国网山东省电力公司东营供电公司 | A comprehensive energy scheduling method and system considering carbon emissions |
| CN116132548B (en) * | 2023-02-06 | 2023-08-15 | 北京思维实创科技有限公司 | A data acquisition method and system for distributed multi-source heterogeneous data |
| CN116151129A (en) * | 2023-04-18 | 2023-05-23 | 石家庄科林电气股份有限公司 | Power dispatching system fault diagnosis method based on extreme learning machine |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855525A (en) * | 2012-08-16 | 2013-01-02 | 中国电力科学研究院 | System and method for forecasting and analyzing load of resident user |
| CN204156611U (en) * | 2014-11-15 | 2015-02-11 | 国网河南省电力公司开封供电公司 | A kind of intelligent distribution network data management and analytical equipment |
| CN104967123A (en) * | 2015-08-03 | 2015-10-07 | 苏州健雄职业技术学院 | Intermittent energy consumption monitoring device and monitoring method under distribution network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7274975B2 (en) * | 2005-06-06 | 2007-09-25 | Gridpoint, Inc. | Optimized energy management system |
| US9785130B2 (en) * | 2014-04-10 | 2017-10-10 | Nec Corporation | Decentralized energy management platform |
-
2016
- 2016-03-22 CN CN201610163622.5A patent/CN105811402B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855525A (en) * | 2012-08-16 | 2013-01-02 | 中国电力科学研究院 | System and method for forecasting and analyzing load of resident user |
| CN204156611U (en) * | 2014-11-15 | 2015-02-11 | 国网河南省电力公司开封供电公司 | A kind of intelligent distribution network data management and analytical equipment |
| CN104967123A (en) * | 2015-08-03 | 2015-10-07 | 苏州健雄职业技术学院 | Intermittent energy consumption monitoring device and monitoring method under distribution network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105811402A (en) | 2016-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105811402B (en) | A kind of Electric Load Prediction System and its Forecasting Methodology | |
| CN113159339B (en) | One-area one-index line loss management method and system based on big data | |
| CN106154209B (en) | Electrical energy meter fault prediction technique based on decision Tree algorithms | |
| US20040225649A1 (en) | Identifying energy drivers in an energy management system | |
| CN106952032A (en) | A kind of equipment manufacture big data management system | |
| CN110782153A (en) | A modeling method and system for comprehensive energy efficiency evaluation system in enterprise parks | |
| CN110928866A (en) | Method and system for line topology verification based on big data analysis of power outage information | |
| CN111191966B (en) | A Method for Identifying Unqualified Periods of Distribution Network Voltage Based on Spatiotemporal Characteristics | |
| CN111291076A (en) | Abnormal water use monitoring and alarming system based on big data and construction method thereof | |
| CN109165763A (en) | A kind of potential complained appraisal procedure and device of 95598 customer service work order | |
| CN117273337A (en) | A smart energy meter evaluation method | |
| CN109035062A (en) | A kind of client's electricity charge anomaly analysis and tactful application system | |
| CN118074126B (en) | Operation and maintenance monitoring method based on power grid information | |
| CN118094262B (en) | A load outlier detection method based on spatial clustering | |
| CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
| Perçuku et al. | Big data and time series use in short term load forecasting in power transmission system | |
| CN117728379A (en) | Intelligent operation scheduling method for regional power grid | |
| CN118485264A (en) | A method for carbon emission accounting and quota allocation in power grid from the perspective of carbon emission trading | |
| CN103501003A (en) | Line loss control system | |
| Siddiquee et al. | A Data-Driven Framework for Quantifying Demand Response Participation Benefit of Industrial Consumers | |
| CN107862476A (en) | A kind of metering table demand computational methods based on data analysis | |
| CN115860983A (en) | Smart city gas safety monitoring operation management method and system based on Internet of things | |
| CN112418548B (en) | Intelligent workshop management method and system based on artificial intelligence technology | |
| CN113642933A (en) | Power distribution station low-voltage diagnosis method and device | |
| CN118798548A (en) | Edge-to-edge integrated management platform for distributed energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |