CN104657786A - Short-term wind power mixed predicting method based on Boosting algorithm - Google Patents

Short-term wind power mixed predicting method based on Boosting algorithm Download PDF

Info

Publication number
CN104657786A
CN104657786A CN201510056771.7A CN201510056771A CN104657786A CN 104657786 A CN104657786 A CN 104657786A CN 201510056771 A CN201510056771 A CN 201510056771A CN 104657786 A CN104657786 A CN 104657786A
Authority
CN
China
Prior art keywords
wind power
day
boosting algorithm
predicting
forecast model
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.)
Pending
Application number
CN201510056771.7A
Other languages
Chinese (zh)
Inventor
蒋宇
陈星莺
廖迎晨
余昆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hohai University HHU
Original Assignee
Hohai University HHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hohai University HHU filed Critical Hohai University HHU
Priority to CN201510056771.7A priority Critical patent/CN104657786A/en
Publication of CN104657786A publication Critical patent/CN104657786A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a short-term wind power mixed predicting method based on a Boosting algorithm. The method comprises the following steps: predicting and training by repeatedly calling a basic predicting model through the Boosting algorithm; generating a corresponding predicting accuracy weight coefficient according to a prediction error of a called model; combining a series of basic predicting models with relatively low predicting precision to form a wind power mixed predicting model with high predicting precision by utilizing the model combination function of the Boosting algorithm. The method disclosed by the invention can directly improve the predicting precision of the wind power predicting method and solve the problem that the wind power predicting effect is poor in a conventional industrial wind power short-term predicting technique, so that the huge purchasing expense of standby generating capacity can be saved for an electrical network enterprise, the operating efficiency of the electrical network enterprise is improved, and moreover, the wind curtailment electric quantity can be effectively reduced, the effective wind power grid connection capacity is improved and energy conservation and emission reduction are realized.

Description

A kind of short-term wind power hybrid forecasting method based on Boosting algorithm
Technical field
The present invention relates to wind power electric powder prediction in generation of electricity by new energy process, particularly relate to a kind of short-term wind power hybrid forecasting method based on Boosting algorithm.
Background technology
Under the whole world is faced with energy crisis and environmental crisis background, wind-power electricity generation is one of the most competitive regenerative resource of following many decades, and wind energy content is huge; utilize wind energy to generate electricity; can not only environmental pollution be reduced, the fuel cost of electric system can also be reduced, bring considerable economic benefit.
Ended for the end of the year 2010, China's wind-powered electricity generation total installed capacity exceedes the U.S., leaps to the first in the world; End in Dec, 2014, the installed capacity of Jiangsu Power Grid grid connected wind power has reached 2,970,000 kilowatts, accounts for 3.7% of Jiangsu Power Grid total installation of generating capacity, becomes the second largest main force power supply being only second to thermoelectricity.Along with the swift and violent growth of wind-power electricity generation installation total amount, the intrinsic intermittence of wind-powered electricity generation self, undulatory property have become the principal element hindering wind power integration electrical network.The each main wind power base in the whole nation is abandoned wind phenomenon and is taken place frequently, and wind-powered electricity generation enterprise has wind not generate electricity, has electricity can not send; Power grid enterprises are wind-powered electricity generation of dissolving to greatest extent simultaneously, and when lacking high-precision wind power prediction technical support, can only improve constantly the margin capacity of genset in generation schedule, this must cause the continuous deterioration of unit generation economy.
Wind-powered electricity generation is predicted accurately, significantly can reduce the impact of wind-powered electricity generation on electrical network.Experience shows, wind-powered electricity generation prognoses system is the key factor reducing generating margin capacity, promote the economic operation level of electric system, improve wind-powered electricity generation permeability accurately and reliably, can be generation of electricity by new energy Real-Time Scheduling simultaneously, generation of electricity by new energy is planned a few days ago, generation of electricity by new energy monthly plan, generation of electricity by new energy capability evaluation and abandon wind-powered electricity generation amount and estimate to provide key message.
Nearly decades, in order to solve the accurately predicting problem of wind-powered electricity generation, scientific research personnel is mainly by Forecasting Methodology, statistical method (the persistence forecasting method based on numerical weather forecast, autoregressive moving average method, artificial neural network method), hybrid forecasting method, the method improving the accuracy of wind energy turbine set wind power prediction is explored, and achieves certain achievement.But the precision of prediction of existing wind power prediction method is still not high, international advanced wind power prediction systematic error, about 15%, can not meet requirement of engineering.Therefore, accelerate to carry out wind power prediction research steps, pinpoint accuracy wind power forecasting system that develop applicable China's national situation as early as possible, that have independent intellectual property right, is significant.
Summary of the invention
Goal of the invention: the object of this invention is to provide a kind of precision of prediction high, abandon the few short-term wind power hybrid forecasting method of wind-powered electricity generation amount.
Technical scheme: for reaching this object, the present invention by the following technical solutions:
Short-term wind power hybrid forecasting method based on Boosting algorithm of the present invention, by iterate training and the model combination function of Boosting algorithm, by wind power combination forecast model high for a series of basic forecast model group synthesis precision of predictions lower for precision of prediction, comprise the following steps:
S1: per diem gathered by the history wind power data of wind energy turbine set to be predicted, obtains the history wind power measured value of wind energy turbine set to be predicted, generates corresponding time series amount;
S2: according to the day F to be measured determined, from the history wind power measured value choosing forward M+1 day F-1 day successively in described time series amount, i.e. the history wind power measured value X={x of τ-M day to τ day τ, x τ-1..., x τ-M, as the training sample set of Boosting algorithm, wherein τ=F-1;
S3: the selected distance day to be measured F history wind power measured value of nearest a day, i.e. the history wind power measured value x of τ day τas the training objective sample of Boosting algorithm, and using τ day as training objective day;
S4: adopt x τ-tas the training input amendment of Boosting algorithm, wherein t ∈ [1, M], adopts x τas M x τ-tcommon training objective sample; After M training, Boosting algorithm generates the lower basic forecast model of M+1 precision of prediction, i.e. h τ-tand h 0, wherein t ∈ [1, M]; Prediction accuracy weight α again τ-tand α 0, and form the high combination forecasting H of precision of prediction, wherein t ∈ [1, M];
S5: adopt x τas the input data of combination forecasting H, to the wind power sequence x of day F to be measured nextcarry out final prediction, i.e. x next=H (x τ);
Wherein, the day in step S1, S2, S3 and S5 all refers to 24 hours.
Further, described step S4 comprises the following steps:
S4.1: access time, sequential forecasting models was as described basic forecast model h τ-t, carry out M prediction, predict with the history wind power measured value x of a day at every turn τ-tas input, predict the wind performance number x of τ day τ-t τ, through basic forecast model h described in M recursive call τ-trear prediction obtains the wind power sequence value { x of τ day τ-1 τ..., x τ-M τ; And according to the history wind power measured value x of τ day τthe described basic forecast model h of independent generation 0;
S4.2: according to the history wind power measured value x of τ day τto each described basic forecast model h τ-tpredict the wind performance number x of the τ day obtained τ-t τcheck, and calculate corresponding predicated error ε τ-t, then according to predicated error ε τ-tcalculate each described basic forecast model h τ-taccuracy weight α τ-t, wherein t ∈ [1, M]; Described basic forecast model h 0accuracy weight be α 0, according to the τ predicated error ε of-1 day τ-1calculate;
S4.3: by described basic forecast model h τ-t, and h 0, and accuracy weight α τ-tand α 0combine, obtain the combination forecasting H that described precision of prediction is high, wherein t ∈ [1, M];
Wherein, the day in step S4.1 and S4.2 all refers to 24 hours.
Further, the time series predicting model in described step S4.1 comprise in arma modeling, AR model, MA model or ANN model any one.
Further, each basic forecast model h in described step S4.2 τ-tpredicated error ε τ-tobtained by following formulae discovery:
ε τ-t＝|x τ-h τ-t(x τ-t)|/p max
Wherein p maxfor the maximum wind power generated output total volume of wind energy turbine set to be predicted, t ∈ [1, M].
Further, each basic forecast model h in described step S4.2 τ-taccuracy weight α τ-tobtained by following formulae discovery:
α τ-t＝ln[ε τ-t/(1-ε τ-t)]/2
Wherein, t ∈ [1, M].
Further, the basic forecast model h in described step S4.2 0accuracy weight α 0obtained by following formulae discovery:
α 0＝(1+ε τ-1)/(10-7ε τ-1)
Further, the combination forecasting H in described step S4.3 is obtained by following formulae discovery:
H＝(α 0*h 0+∑α τ-t*h τ-t)/(α 0+∑α τ-t)
Wherein, t ∈ [1, M].
Beneficial effect: the present invention directly can improve the precision of prediction of wind power prediction method, solve the problem of the wind power prediction weak effect that current industrial wind power short-term forecasting technology exists, huge reserve generation capacity buying expenses can be saved for power grid enterprises, improve power grid enterprises' operation benefits, effectively can reduce simultaneously and abandon wind-powered electricity generation amount, improve the effective grid connection capacity of wind-powered electricity generation, realize energy-saving and emission-reduction.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is the implementation procedure of step S4 of the present invention;
Fig. 3 is the contrast of the prediction effect of the present invention and traditional arma modeling.
Embodiment
Below in conjunction with accompanying drawing, further illustrate technical scheme of the present invention by embodiment.
Fig. 1 is process flow diagram of the present invention.See Fig. 1, short-term wind power hybrid forecasting method based on Boosting algorithm of the present invention, by iterate training and the model combination function of Boosting algorithm, by wind power combination forecast model high for a series of basic forecast model group synthesis precision of predictions lower for precision of prediction, comprise the following steps:
S1: per diem gathered by the history wind power data of each wind energy turbine set, obtains the history wind power measured value of each wind energy turbine set, generates corresponding time series amount;
S2: according to the day F to be measured determined, from the history wind power measured value choosing forward M+1 day F-1 day successively in described time series amount, i.e. the history wind power measured value X={x of τ-M day to τ day τ, x τ-1..., x τ-M, as the training sample set of Boosting algorithm, wherein τ=F-1;
S3: the selected distance day to be measured F history wind power measured value of nearest a day, i.e. the history wind power measured value x of τ day τas the training objective sample of Boosting algorithm, and using τ day as training objective day;
S4: adopt x τ-tas the training input amendment of Boosting algorithm, wherein t ∈ [1, M], adopts x τas M x τ-tcommon training objective sample; After M training, Boosting algorithm generates the lower basic forecast model of M+1 precision of prediction, i.e. h τ-tand h 0, wherein t ∈ [1, M]; Prediction accuracy weight α again τ-tand α 0, and form the high combination forecasting H of precision of prediction, wherein t ∈ [1, M];
S5: adopt x τas the input data of combination forecasting H, to the wind power sequence x of day F to be measured nextcarry out final prediction, i.e. x next=H (x τ);
Wherein, the day in step S1, S2, S3 and S5 all refers to 24 hours.
Concrete, step S4 comprises three sub-steps, as shown in Figure 2, that is:
S4.1: access time, sequential forecasting models was as described basic forecast model h τ-t, carry out M prediction, predict with the history wind power measured value x of a day at every turn τ-tas input, predict the wind performance number x of τ day τ-t τ, through basic forecast model h described in M recursive call τ-trear prediction obtains the wind power sequence value { x of τ day τ-1 τ..., x τ-M τ; And according to the history wind power measured value x of τ day τthe described basic forecast model h of independent generation 0;
S4.2: according to the history wind power measured value x of τ day τto each described basic forecast model h τ-tpredict the wind performance number x of the τ day obtained τ-t τcheck, and calculate corresponding predicated error ε τ-t, then according to predicated error ε τ-tcalculate each described basic forecast model h τ-taccuracy weight α τ-t, wherein t ∈ [1, M]; Described basic forecast model h 0accuracy weight be α 0, according to the τ predicated error ε of-1 day τ-1calculate;
S4.3: by described basic forecast model h τ-t, and h 0, and accuracy weight α τ-tand α 0combine, obtain the combination forecasting H that described precision of prediction is high, wherein t ∈ [1, M];
Wherein, the day in step S4.1 and S4.2 all refers to 24 hours.
Wherein, the time series predicting model in step S4.1 comprise in arma modeling, AR model, MA model or ANN model any one.
In addition, each basic forecast model h in step S4.2 τ-tpredicated error ε τ-tobtained by following formulae discovery:
ε τ-t＝|x τ–h τ-t(x τ-t)|/p max(1)
Wherein p maxfor the maximum wind power generated output total volume of wind energy turbine set to be predicted, t ∈ [1, M].
According to the predicated error ε that formula (1) calculates τ-t, each basic forecast model h in step S4.2 τ-taccuracy weight α τ-tobtained by following formulae discovery:
α τ-t＝ln[ε τ-t/(1-ε τ-t)]/2 (2)
Wherein, t ∈ [1, M].
The τ predicated error ε of-1 day is calculated according to formula (1) τ-1, the basic forecast model h in step S4.2 0accuracy weight α 0obtained by following formulae discovery:
α 0＝(1+ε τ-1)/(10-7ε τ-1) (3)
Further, the combination forecasting H in step S4.3 is obtained by following formulae discovery:
H＝(α 0*h 0+∑α τ-t*h τ-t)/(α 0+∑α τ-t) (4)
Wherein, t ∈ [1, M].
In order to verify the advantage of the present invention relative to Classical forecast model further, predicting the outcome after Fig. 3 provides in July, 2,012 one, Jiangsu wind energy turbine set application the inventive method, and adopt predicting the outcome of traditional arma modeling, and give actual measurement wind power data.As seen in Figure 3, the wind power prediction result after the inventive method is applied larger with actual measurement wind power data degree of agreement.Draw according to measuring and calculating, the prediction effect of " autoregressive moving-average model (arma modeling) " that the prediction effect of the inventive method adopts than Traditional project improves 6.516%.
Therefore, the present invention directly can improve the precision of prediction of wind power prediction method, solve the problem of the wind power prediction weak effect that current industrial wind power short-term forecasting technology exists, huge reserve generation capacity buying expenses can be saved for power grid enterprises, improve power grid enterprises' operation benefits, effectively can reduce simultaneously and abandon wind-powered electricity generation amount, improve the effective grid connection capacity of wind-powered electricity generation, realize energy-saving and emission-reduction.

Claims (7)

1. the short-term wind power hybrid forecasting method based on Boosting algorithm, it is characterized in that: adopt Boosting algorithm, by wind power combination forecast model high for a series of basic forecast model group synthesis precision of predictions lower for precision of prediction, comprise the following steps:
S1: per diem gathered by the history wind power data of wind energy turbine set to be predicted, obtains the history wind power measured value of wind energy turbine set to be predicted, generates corresponding time series amount;
S2: according to the day F to be measured determined, from the history wind power measured value choosing forward M+1 day F-1 day successively in described time series amount, i.e. the history wind power measured value X={x of τ-M day to τ day τ, x τ-1..., x τ-M, as the training sample set of Boosting algorithm, wherein τ=F-1;
S3: the selected distance day to be measured F history wind power measured value of nearest a day, i.e. the history wind power measured value x of τ day τas the training objective sample of Boosting algorithm, and using τ day as training objective day;
S4: adopt x τ-tas the training input amendment of Boosting algorithm, wherein t ∈ [1, M], adopts x τas M x τ-tcommon training objective sample; After M training, Boosting algorithm generates the lower basic forecast model of M+1 precision of prediction, i.e. h τ-tand h 0, wherein t ∈ [1, M]; Prediction accuracy weight α again τ-tand α 0, and form the high combination forecasting H of precision of prediction, wherein t ∈ [1, M];
S5: adopt x τas the input data of combination forecasting H, to the wind power sequence x of day F to be measured nextcarry out final prediction, i.e. x next=H (x τ);
Wherein, the day in step S1, S2, S3 and S5 all refers to 24 hours.
2. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 1, is characterized in that: described step S4 comprises the following steps:
S4.1: access time, sequential forecasting models was as described basic forecast model h τ-t, carry out M prediction, predict with the history wind power measured value x of a day at every turn τ-tas input, predict the wind performance number x of τ day τ-t τ, through basic forecast model h described in M recursive call τ-trear prediction obtains the wind power sequence value { x of τ day τ-1 τ..., x τ-M τ; And according to the history wind power measured value x of τ day τthe described basic forecast model h of independent generation 0;
S4.2: according to the history wind power measured value x of τ day τto each described basic forecast model h τ-tpredict the wind performance number x of the τ day obtained τ-t τcheck, and calculate corresponding predicated error ε τ-t, then according to predicated error ε τ-tcalculate each described basic forecast model h τ-taccuracy weight α τ-t, wherein t ∈ [1, M]; Described basic forecast model h 0accuracy weight be α 0, according to the τ predicated error ε of-1 day τ-1calculate;
S4.3: by described basic forecast model h τ-t, and h 0, and accuracy weight α τ-tand α 0combine, obtain the combination forecasting H that described precision of prediction is high, wherein t ∈ [1, M];
Wherein, the day in step S4.1 and S4.2 all refers to 24 hours.
3. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 2, is characterized in that: the time series predicting model in described step S4.1 comprise in arma modeling, AR model, MA model or ANN model any one.
4. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 2, is characterized in that: each basic forecast model h in described step S4.2 τ-tpredicated error ε τ-tobtained by following formulae discovery:
ε τ-t＝|x τ-h τ-t(x τ-t)|/p max
Wherein p maxfor the maximum wind power generated output total volume of wind energy turbine set to be predicted, t ∈ [1, M].
5. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 2, is characterized in that: each basic forecast model h in described step S4.2 τ-taccuracy weight α τ-tobtained by following formulae discovery:
α τ-t＝ln[ε τ-t/(1-ε τ-t)]/2
Wherein, t ∈ [1, M].
6. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 2, is characterized in that: the basic forecast model h in described step S4.2 0accuracy weight α 0obtained by following formulae discovery:
α 0＝(1+ε τ-1)/(10-7ε τ-1) 。
7. the short-term wind power hybrid forecasting method based on Boosting algorithm according to claim 2, is characterized in that: the combination forecasting H in described step S4.3 is obtained by following formulae discovery:
H＝(α 0*h 0+∑α τ-t*h τ-t)/(α 0+∑α τ-t)
Wherein, t ∈ [1, M].
CN201510056771.7A 2015-02-03 2015-02-03 Short-term wind power mixed predicting method based on Boosting algorithm Pending CN104657786A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510056771.7A CN104657786A (en) 2015-02-03 2015-02-03 Short-term wind power mixed predicting method based on Boosting algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510056771.7A CN104657786A (en) 2015-02-03 2015-02-03 Short-term wind power mixed predicting method based on Boosting algorithm

Publications (1)

Publication Number Publication Date
CN104657786A true CN104657786A (en) 2015-05-27

Family

ID=53248883

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510056771.7A Pending CN104657786A (en) 2015-02-03 2015-02-03 Short-term wind power mixed predicting method based on Boosting algorithm

Country Status (1)

Country Link
CN (1) CN104657786A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107947210A (en) * 2017-11-27 2018-04-20 甘肃省电力公司风电技术中心 A kind of energy storage for stabilizing the level fluctuation of output of wind electric field minute goes out force control method
CN109800923A (en) * 2019-02-22 2019-05-24 南方电网科学研究院有限责任公司 distributed wind power generation short-term power combination prediction method
CN109903071A (en) * 2017-12-11 2019-06-18 优估（上海）信息科技有限公司 A kind of used car pricing method, device, equipment and computer-readable medium
CN113095547A (en) * 2021-03-18 2021-07-09 国网辽宁省电力有限公司 Short-term wind power prediction method based on GRA-LSTM-ICE model

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102129511A (en) * 2011-02-21 2011-07-20 北京航空航天大学 System for forecasting short-term wind speed of wind power station based on MATLAB
CN102521671A (en) * 2011-11-29 2012-06-27 华北电力大学 Ultrashort-term wind power prediction method
CN102663513A (en) * 2012-03-13 2012-09-12 华北电力大学 Combination forecast modeling method of wind farm power by using gray correlation analysis
CN103279804A (en) * 2013-04-29 2013-09-04 清华大学 Super short-period wind power prediction method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102129511A (en) * 2011-02-21 2011-07-20 北京航空航天大学 System for forecasting short-term wind speed of wind power station based on MATLAB
CN102521671A (en) * 2011-11-29 2012-06-27 华北电力大学 Ultrashort-term wind power prediction method
CN102663513A (en) * 2012-03-13 2012-09-12 华北电力大学 Combination forecast modeling method of wind farm power by using gray correlation analysis
CN103279804A (en) * 2013-04-29 2013-09-04 清华大学 Super short-period wind power prediction method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吴俊利: "基于Adaboost的BP神经网络改进算法在短期风速预测中的应用", 《电网技术》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107947210A (en) * 2017-11-27 2018-04-20 甘肃省电力公司风电技术中心 A kind of energy storage for stabilizing the level fluctuation of output of wind electric field minute goes out force control method
CN107947210B (en) * 2017-11-27 2021-06-22 甘肃省电力公司风电技术中心 Energy storage output control method for stabilizing wind power plant output minute-level fluctuation
CN109903071A (en) * 2017-12-11 2019-06-18 优估（上海）信息科技有限公司 A kind of used car pricing method, device, equipment and computer-readable medium
CN109800923A (en) * 2019-02-22 2019-05-24 南方电网科学研究院有限责任公司 distributed wind power generation short-term power combination prediction method
CN109800923B (en) * 2019-02-22 2023-05-23 南方电网科学研究院有限责任公司 Short-term power combination prediction method for distributed wind power generation
CN113095547A (en) * 2021-03-18 2021-07-09 国网辽宁省电力有限公司 Short-term wind power prediction method based on GRA-LSTM-ICE model
CN113095547B (en) * 2021-03-18 2023-09-26 国网辽宁省电力有限公司 Short-term wind power prediction method based on GRA-LSTM-ICE model

Similar Documents

Publication Publication Date Title
CN109523128B (en) Renewable energy source capacity configuration method for promoting digestion
CN108123492B (en) A kind of generation schedule optimization method a few days ago considering thermoelectricity electric heat storage combined adjusting peak
CN102694391B (en) Day-ahead optimal scheduling method for wind-solar storage integrated power generation system
CN109767078B (en) Multi-type power supply maintenance arrangement method based on mixed integer programming
CN107134810B (en) Independent micro-energy-grid energy storage system optimal configuration solving method
CN107944757A (en) Electric power interacted system regenerative resource digestion capability analysis and assessment method
CN102419394B (en) Wind/solar power prediction method with variable prediction resolution
CN113850474B (en) Thermoelectric hydrogen multi-energy flow comprehensive energy system and optimal scheduling method thereof
CN104143839B (en) Wind power plant cluster based on power prediction limits active power distribution method of exerting oneself
CN104268659A (en) Photovoltaic power station generated power super-short-term prediction method
CN104657786A (en) Short-term wind power mixed predicting method based on Boosting algorithm
CN106257792B (en) A kind of new energy priority scheduling method based on two stages Unit Combination
CN103986193B (en) A kind of method that maximum wind grid connection capacity obtains
CN109378856A (en) Wind based on rolling optimization-storage hybrid power plant power swing stabilizes strategy and analogy method
CN110932261A (en) Multi-energy system combined installation planning method based on global benefit maximization
Chang et al. Model predictive control based energy collaborative optimization management for energy storage system of virtual power plant
CN116402210A (en) Multi-objective optimization method, system, equipment and medium for comprehensive energy system
CN108667077A (en) A kind of wind storage association system Optimization Scheduling
CN104239962A (en) Regional power grid total wind power short-term prediction method based on correlation analysis
CN111178733B (en) Abandoned wind power evaluation method based on equivalent electric quantity function method
CN104657787A (en) Wind power time series combined prediction method
Han et al. Analysis of economic operation model for virtual power plants considering the uncertainties of renewable energy power generation
CN113394820A (en) Optimized scheduling method for new energy grid-connected power system
Ai et al. Study on transmission planning of combined wind and storage system
CN105939013A (en) Generation right replacement power estimation method of wind farm to minimize wind curtailment power

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20150527