CN104680246A - Wind power plant real-time power predication method based on data driving - Google Patents
Wind power plant real-time power predication method based on data driving Download PDFInfo
- Publication number
- CN104680246A CN104680246A CN201510044845.5A CN201510044845A CN104680246A CN 104680246 A CN104680246 A CN 104680246A CN 201510044845 A CN201510044845 A CN 201510044845A CN 104680246 A CN104680246 A CN 104680246A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- moment
- wind energy
- power
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000005259 measurement Methods 0.000 claims description 11
- 238000010248 power generation Methods 0.000 abstract description 6
- 238000004146 energy storage Methods 0.000 abstract description 4
- 230000005611 electricity Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Wind Motors (AREA)
Abstract
The invention provides a wind power plant real-time power predication method based on data driving. The method comprises the following steps: S1: applying a mathematical point-slope form method to calculating an estimated value of real-time output power of the next moment of a wind power plant according to an actual output power numerical value of the last moment of the wind power plant; taking the estimated value as a real-time recursion power numerical value of the wind power plant at the mth moment; S2: revising the estimated value of the real-time output power of the wind power plant in the step S1 by adopting a moving average method; taking a revised value of the estimated value as a real-time recursion predicated power value of the wind power plant at the mth moment; and S3: calculating an expected power generation power value of an energy storage system. Compared with a traditional method for delaying post-dispatching of a wind storage power station, the requirements of power grid dispatching can be rapidly responded by the wind storage power station; the method is simple and is easy to realize.
Description
Technical field
The invention belongs to wind electricity storage station technical field of power generation, be specifically related to a kind of wind energy turbine set realtime power Forecasting Methodology based on data-driven.
Background technology
Country's wind-light storage transmission demonstration project is positioned at Zhangjiakou City Zhangbei County, Hebei province and Shangyi County, the energy-accumulating power station of planning construction 500MW wind energy turbine set, 100MW photo-voltaic power generation station and respective volume.Due to wind, the light energy is intrinsic for the first time randomness, undulatory property and intermittence, it is concentrated grid-connected that large-scale wind Generate, Generation, Generator volt generates electricity, and certainly will bring lot of challenges to the operation of electric system, scheduling and controlling etc.In the research exploring solution route, extensive energy storage technology arises at the historic moment.In succession carry out multinomial demonstration project abroad, establish and improve fitful power controllability by energy storage technology, improve its grid-connected application power.
Summary of the invention
The present invention is directed to Zhangbei County's wind-light storage transmission demonstration project-wind storing cogeneration to operate in and follow the tracks of generation schedule pattern, the real-time output power of prediction wind energy turbine set, and then calculate and control the generating of accumulator system.
In order to realize above object, the present invention is achieved through the following technical solutions:
First according to the actual measurement output power data of wind energy turbine set, slope variation Forecasting Methodology and moving average method is adopted, the real-time output power value of prediction and calculation wind energy turbine set subsequent time; Then according to the dispatch command of national grid, calculate the expectation power generation values of accumulator system, make wind storing cogeneration meet dispatching of power netwoks demand.
The computing method of the real-time output power of prediction wind energy turbine set, be utilize the actual measurement output power data in wind energy turbine set m-1 moment to carry out recursion to obtain wind energy turbine set m moment recursion power data, Fig. 1 is real time sequence figure.The method comprises following concrete steps:
S1: according to the actual measurement output power numerical value in a moment in wind energy turbine set, applied mathematics point slope form method calculates the estimated value of wind energy turbine set subsequent time real-time output power, and using this estimated value as the real-time recursion magnitude of power of wind energy turbine set in the m moment.
This step adopts mathematics point slope form method to carry out according to the actual measurement output power numerical value in m-2, m-1 moment the estimated value that recursion obtains m moment real-time output power.
The mathematical formulae of the real-time recursion of foundation mathematics point slope form is as shown in formula (1), (2)
y'
m＝y
m-1+k
m-1,m*Δt (1)
Wherein: y '
mthe wind energy turbine set that adopts slope recursion the to obtain estimation output power in the m moment, y
m-1the measured data in wind energy turbine set m-1 moment, K
m-1, mbe wind energy turbine set m-1 moment and m moment measured data between slope, Δ t=1min.
Following problem is there will be: first by the data of mathematics slope recurrence method prediction subsequent time, because the method for slope stepwise predict is the measured data of removing stepwise predict subsequent time based on the measured data of previous moment and the change of slope, so when measured power data, when rising or downtrending is constant, larger fluctuation occur, the real time data adopting the method stepwise predict to obtain will be larger with the error between measured data; Secondly, when the variation tendency of measured power data is become decline from rising or become rising from decline, time delay and the sudden change of stepwise predict data can be caused.If the change of measured power data relatively steadily slowly time, the method for slope stepwise predict can be adopted to carry out the data of recursion actual measurement.
Because slope stepwise predict method only considers that the nearest data of history are on the impact of Future Data, precision of prediction in this way can not be too high.But fairly simple being easy to of the method is applied in engineering practice, so need the real time data estimated value obtained mathematics slope stepwise predict to carry out moving average process correction.
S2: adopt moving average method to revise, using the real-time stepwise predict performance number of the modified value of estimated value as the wind energy turbine set m moment to the estimated value of the real-time output power of wind energy turbine set that step S1 recursion obtains.
Moving average method carries out slip process to the real time data adopting slope stepwise predict method to obtain in step S1.Problem due to the precision of prediction of slope stepwise predict method can increase the fluctuation of wind energy turbine set measured power data, so adopt moving average method effectively can also reduce the fluctuation of wind energy turbine set stepwise predict realtime power.
Employing moving average method is the modified value y to the history real time data obtained after the stepwise predict+moving average of employing slope
iwith the real-time estimated value y' that the m moment only obtains through slope stepwise predict method
mcarry out sum-average arithmetic calculating, in the result step of replacing S1 obtained, adopt the real-time data estimator of mathematics slope recursion.The expression formula of moving average method is such as formula shown in (3).
Wherein, N is the number of the history real time data obtained after adopting slope stepwise predict and moving average, y
m-i, i=0,1 ..., N is the modified value of the history real time data obtained after adopting slope stepwise predict+moving average, y'
mit is the estimated value of the real-time recursion data in the m moment obtained by slope stepwise predict method.
The precision of prediction of slope recursion+running mean method is adopted to be higher than the precision of prediction only adopting slope stepwise predict method.
S3: according to wind storing cogeneration power station in the generation schedule power in m moment and the real-time output power through the wind energy turbine set m moment that step S1, S2 calculate, calculates the expectation generated output value of accumulator system.Accumulator system is do algebraically by the generation schedule performance number in m moment power station and the predicted value of the output power in wind energy turbine set m moment to subtract each other and obtain at the expectation generated output in m moment.
For extending the serviceable life of accumulator system, need the Real-time Feedback value of the constraint condition affecting accumulator system serviceable life according to the discharge and recharge degree of depth, rated power, rated capacity etc. of accumulator system, the expectation generated output value of accumulator system is revised in real time, and then avoids accumulator system to occur breaking through the phenomenon of putting.
The inventive method and traditional delay are dispatched wind electricity storage station method afterwards and are contrasted, and wind electricity storage station can be enable to respond the demand of state's network regulation degree rapidly, and the method is simple, are easy to realize.
Accompanying drawing explanation
Fig. 1 real time sequence figure of the present invention.
The real-time the fundamentals of successive deduction figure of Fig. 2 mathematics of the present invention point slope form.
Fig. 3 accumulator system Generation Control of the present invention strategy block diagram.
Tu4Shi Zhangbei County wind energy turbine set is at the curve map of relatively more steady curve and the grid generation plan slowly of output power change on January 22.
Tu5Shi Zhangbei County wind energy turbine set January 9 output-power fluctuation change greatly the curve map of curve and grid generation plan more rapidly.
Fig. 6 adopts slope recursion+running mean method and slope stepwise predict method to carry out to the output power curve of wind energy turbine set in Fig. 3 the curve map that stepwise predict obtains respectively.
Fig. 7 adopts slope recursion+running mean method and slope stepwise predict method to carry out to the output power curve of wind energy turbine set in Fig. 5 the curve map that stepwise predict obtains respectively.
Fig. 8 is the tracking effect figure being made generation schedulecurve in the output power curve tracing figure 4 of wind storing cogeneration by the generating of control accumulator system.
Fig. 9 is the tracking effect figure being made generation schedulecurve in the output power curve tracing figure 5 of wind storing cogeneration by the generating of control accumulator system.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in more detail.
The invention provides the computing method of the method for the real-time output power prediction of a kind of wind electricity storage station wind energy turbine set and the accumulator system generating of power station real-time follow-up state net generation schedule.In order to realize the schedulable of new forms of energy wind/light/honourable electric field output power, needing to apply the output power that accumulator system improves wind-powered electricity generation and photovoltaic generation, being used for real-time follow-up generation schedule for Zhangbei County's wind-light storage transmission demonstration project-accumulator system and being described.
Extract Zhangbei County wind energy turbine set output power change in January relatively slowly and the actual measurement output power curve of two days that changes greatly of output-power fluctuation and generation schedulecurve as shown in Figure 4,5.Can find out to there is deviation between the measured power curve of wind energy turbine set and the generation schedulecurve of electrical network from Fig. 4,5, or therefore need the generating controlling accumulator system to carry out making up reducing deviation.Due to the restriction of the constraint condition such as rated capacity and rated power of accumulator system, so wind storing cogeneration there will be the powertrace not catching up with generation schedule within some time period.
Because wind electricity storage station is in actual motion, the real-time output power of wind-powered electricity generation can not be known in advance, so adopt the real-time output power data of slope recursion and slope recursion+moving average method prediction wind-powered electricity generation subsequent time respectively.Fig. 6 adopts above-mentioned two kinds of stepwise predicts to obtain to the real-time output power curve of Fig. 4 wind energy turbine set respectively, and dot-and-dash line wherein adopts slope recursion+moving average method to predict the real-time output power curve of wind energy turbine set obtained; Line adopts slope recurrence method to predict the real-time output power curve of wind energy turbine set obtained; Solid line is the actual measurement output power curve of wind energy turbine set.Fig. 7 adopts above-mentioned two kinds of stepwise predicts to obtain to the real-time output power curve of Fig. 5 wind energy turbine set respectively, and dot-and-dash line wherein adopts slope recursion+moving average method to predict the real-time output power curve of wind energy turbine set obtained; Line adopts slope recurrence method to predict the real-time output power curve of wind energy turbine set obtained; Solid line is the actual measurement output power curve of wind energy turbine set.Comparison diagram 6, Fig. 7 can find out that employing slope recursion+moving average method predicts that the deviation between the real-time output power curve of the wind energy turbine set obtained and the actual measurement output power curve of wind energy turbine set is smaller; Employing slope recurrence method predicts that the deviation ratio between the real-time output power curve of wind energy turbine set and the actual measurement output power curve of wind energy turbine set obtained is comparatively large, and the deviation amplitude in Fig. 7 is greater than the deviation amplitude in Fig. 6.Illustrate it is no matter that relatively steadily curve or output-power fluctuation change greatly curve more rapidly slope recursion+moving average method can be adopted to carry out stepwise predict slowly in output power change.
According to the expectation power generation values of the mathematic interpolation accumulator system between the generation schedule dispatch command of electrical network and the real-time output power of the wind energy turbine set that adopts slope recursion+moving average method stepwise predict to obtain, revise the expectation power generation values of energy storage in real time according to the constraint condition such as the discharge and recharge degree of depth, rated power, rated capacity of accumulator system.Fig. 8 is the design sketch of generation schedulecurve in wind storing cogeneration tracing figure 2; Fig. 9 is the design sketch of generation schedulecurve in wind storing cogeneration tracing figure 5.Generating due to accumulator system can be subject to the restriction of the constraint condition such as the discharge and recharge degree of depth, rated power of accumulator system, so the tracking effect of wind storing cogeneration can be affected as shown in Figure 9.
Table one adopts two kinds of methods to predict the qualification rate of the output power of the wind energy turbine set obtained more than 80% and accuracy rate respectively, when output power fluctuation of wind farm randomness is larger as can be seen from Table I, adopt the accuracy rate of two kinds of power forecasting methods difference larger.In the process of the present invention in slope recursion+shifting and averaging prediction method be practically applicable to very much the prediction of Power Output for Wind Power Field.
Table one
Claims (4)
1., based on a wind energy turbine set realtime power Forecasting Methodology for data-driven, it is characterized in that, the method comprises the following steps:
S1: according to the actual measurement output power numerical value in a moment in wind energy turbine set, applied mathematics point slope form method calculates the estimated value of wind energy turbine set subsequent time real-time output power, and using this estimated value as the real-time recursion magnitude of power of wind energy turbine set in the m moment;
S2: adopt moving average method to revise, using the real-time stepwise predict performance number of the modified value of estimated value as the wind energy turbine set m moment to the estimated value of the real-time output power of wind energy turbine set that step S1 recursion obtains;
S3: the expectation generated output value calculating accumulator system.
2. method according to claim 1, is characterized in that, in described step S1, the mathematical formulae of the real-time recursion of estimated value foundation mathematics point slope form of the real-time output power of wind energy turbine set subsequent time calculates:
y'
m＝y
m-1+k
m-1,m*Δt (1)
Wherein: y '
mthe wind energy turbine set that adopts slope recursion the to obtain estimation output power in the m moment, y
m-1the measured data in wind energy turbine set m-1 moment, K
m-1, mbe wind energy turbine set m-1 moment and m moment measured data between slope, Δ t=1min.
3. method according to claim 1, is characterized in that, in described step S2, employing moving average method is the modified value y to the history real time data obtained after the stepwise predict+moving average of employing slope
iwith the real-time estimated value y' that the m moment only obtains through slope stepwise predict method
mcarry out sum-average arithmetic calculating, in the result step of replacing S1 obtained, adopt the real-time data estimator of mathematics slope recursion;
Wherein, N is the number of the history real time data obtained after adopting slope stepwise predict and moving average, y
m-i, i=0,1 ..., N is the modified value of the history real time data obtained after adopting slope stepwise predict+moving average, y'
mit is the estimated value of the real-time recursion data in the m moment obtained by slope stepwise predict method.
4. method according to claim 1, is characterized in that, the expectation generated output value of accumulator system described in step S3 does algebraically by the generation schedule performance number in m moment power station and the predicted value of the output power in wind energy turbine set m moment to subtract each other and obtain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510044845.5A CN104680246B (en) | 2015-01-29 | 2015-01-29 | A kind of wind power plant realtime power Forecasting Methodology based on data-driven |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510044845.5A CN104680246B (en) | 2015-01-29 | 2015-01-29 | A kind of wind power plant realtime power Forecasting Methodology based on data-driven |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104680246A true CN104680246A (en) | 2015-06-03 |
| CN104680246B CN104680246B (en) | 2017-12-12 |
Family
ID=53315255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510044845.5A Expired - Fee Related CN104680246B (en) | 2015-01-29 | 2015-01-29 | A kind of wind power plant realtime power Forecasting Methodology based on data-driven |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104680246B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105552970A (en) * | 2016-02-25 | 2016-05-04 | 华北电力科学研究院有限责任公司 | Method and apparatus for improving accuracy of predicting power of wind power station |
| CN113705862A (en) * | 2021-08-12 | 2021-11-26 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Method for correcting ultra-short-term new energy prediction data in electric power spot market environment |
| US20230043165A1 (en) * | 2020-08-25 | 2023-02-09 | Tongji University | Mpc-based hierarchical coordinated control method and device for wind-hydrogen coupling system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521671A (en) * | 2011-11-29 | 2012-06-27 | 华北电力大学 | Ultrashort-term wind power prediction method |
| US20140195159A1 (en) * | 2013-01-09 | 2014-07-10 | Iteris, Inc. | Application of artificial intelligence techniques and statistical ensembling to forecast power output of a wind energy facility |
| CN103927597A (en) * | 2014-04-22 | 2014-07-16 | 国家电网公司 | Ultra-short-term wind power prediction method based on autoregression moving average model |
-
2015
- 2015-01-29 CN CN201510044845.5A patent/CN104680246B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521671A (en) * | 2011-11-29 | 2012-06-27 | 华北电力大学 | Ultrashort-term wind power prediction method |
| US20140195159A1 (en) * | 2013-01-09 | 2014-07-10 | Iteris, Inc. | Application of artificial intelligence techniques and statistical ensembling to forecast power output of a wind energy facility |
| CN103927597A (en) * | 2014-04-22 | 2014-07-16 | 国家电网公司 | Ultra-short-term wind power prediction method based on autoregression moving average model |
Non-Patent Citations (2)
| Title |
|---|
| SS SOMAN 等: "A review of wind power and wind speed forecasting methods with different time horizons", 《NORTH AMERICAN POWER SYMPOSIUM》 * |
| 唐波 等: "基于时间序列的风电功率日前预测模型及其应用", 《水电能源科学》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105552970A (en) * | 2016-02-25 | 2016-05-04 | 华北电力科学研究院有限责任公司 | Method and apparatus for improving accuracy of predicting power of wind power station |
| US20230043165A1 (en) * | 2020-08-25 | 2023-02-09 | Tongji University | Mpc-based hierarchical coordinated control method and device for wind-hydrogen coupling system |
| CN113705862A (en) * | 2021-08-12 | 2021-11-26 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Method for correcting ultra-short-term new energy prediction data in electric power spot market environment |
| CN113705862B (en) * | 2021-08-12 | 2024-02-13 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Ultra-short-term new energy prediction data correction method in electric power spot market environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104680246B (en) | 2017-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Adaptive condition predictive-fuzzy PID optimal control of start-up process for pumped storage unit at low head area | |
| Qi et al. | A distributed control framework for smart grid development: Energy/water system optimal operation and electric grid integration | |
| Biegel et al. | Distributed low-complexity controller for wind power plant in derated operation | |
| CN104036334B (en) | A kind of step power station Multiobjective Optimal Operation mixed search algorithm of be coupled peak regulation and navigation demand | |
| CN104993522A (en) | Active power distribution network multi-time scale coordinated optimization scheduling method based on MPC | |
| WO2023216780A1 (en) | Peak regulation optimization scheduling method for cascaded hydro-photovoltaic complementary power generation system | |
| CN110581571A (en) | dynamic optimization scheduling method for active power distribution network | |
| CN102419394B (en) | Wind/solar power prediction method with variable prediction resolution | |
| Vigna et al. | Modelling and simulation of variable speed pico hydel energy storage system for microgrid applications | |
| Deng et al. | Dynamic analysis of variable-speed pumped storage plants for mitigating effects of excess wind power generation | |
| CN104092250A (en) | Distributed economic dispatch and coordination control method for micro-grid system | |
| CN106886839B (en) | Hybrid integer programming-based water-fire-electricity generator set combination optimization scheduling method | |
| Qudaih et al. | Model predictive based load frequency control design in the presence of DFIG wind turbine | |
| Tsai et al. | A novel MPPT control design for wind-turbine generation systems using neural network compensator | |
| CN103986193B (en) | A kind of method that maximum wind grid connection capacity obtains | |
| CN105184426A (en) | Cascade hydropower station peak regulating method based on random continuous optimization strategy | |
| Bernard et al. | Ant-based optimal tuning of PID controllers for load frequency control in power systems | |
| CN104680246A (en) | Wind power plant real-time power predication method based on data driving | |
| CN105305463A (en) | Reactive power optimization method based on stochastic load flow with consideration of photovoltaic power generation and harmonic pollution | |
| Ma et al. | Coordinated control of micro-grid based on distributed moving horizon control | |
| CN104657786A (en) | Short-term wind power mixed predicting method based on Boosting algorithm | |
| Cai et al. | A machine learning-based model predictive control method for pumped storage systems | |
| CN104184165A (en) | Cooperative control method applicable to photovoltaic generator set without main control center | |
| Yang et al. | Assessing the dispatch flexibility of coordinated solar and hydro generation | |
| Xu et al. | Design of three-stage start-up optimal strategy based on fuzzy fractional-order proportion integration differentiation controller of pumped storage unit under low water head |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171212 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |