CN111222738B - Method for predicting power and optimizing parameters of wind power cluster - Google Patents
Method for predicting power and optimizing parameters of wind power cluster Download PDFInfo
- Publication number
- CN111222738B CN111222738B CN201910991503.2A CN201910991503A CN111222738B CN 111222738 B CN111222738 B CN 111222738B CN 201910991503 A CN201910991503 A CN 201910991503A CN 111222738 B CN111222738 B CN 111222738B
- Authority
- CN
- China
- Prior art keywords
- data set
- parameters
- predicted
- prediction
- historical
- 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 38
- 238000005457 optimization Methods 0.000 claims abstract description 27
- 238000000513 principal component analysis Methods 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 7
- 241000669244 Unaspis euonymi Species 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 238000007418 data mining Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013341 scale-up Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting power and optimizing parameters of a wind power cluster, which divides historical NWP data and historical power data into two independent data sets and optimizes the parameters in three stages; performing principal component analysis on an original wind speed vector, taking the result of the principal component analysis as the input of a wind power cluster power prediction model, and dividing two independent data sets into a data set to be predicted and a historical data set respectively; calculating Euclidean characteristic distance between an input data matrix of the prediction point and a historical data set, comparing the Euclidean characteristic distance with a threshold value delta to obtain a data set with the highest matching degree and a prediction data set, judging whether optimization is finished, and otherwise, setting parameter values by a variable-scale network search method to continuously optimize to obtain four parameters with the minimum overall prediction error; and controlling three parameter values of the obtained four initial optimized values of the parameters to be unchanged, and changing the remaining one parameter value until the optimal four parameter combinations are obtained. The method has high prediction precision and popularization value.
Description
Technical Field
The invention relates to a method for predicting power and optimizing parameters of a wind power cluster, and belongs to the field of new energy power prediction.
Background
Wind energy is mainly influenced by natural factors and has the characteristics of randomness, volatility, intermittence and the like, so that the phenomena of voltage deviation, frequency deviation, voltage fluctuation, even grid disconnection and the like can occur after large-scale wind power grid connection, along with the rapid increase of the scale of the wind power grid connection, the influence of uncertainty of wind power on the stability, the abundance and the economy of a power system and a power market is more and more obvious, the wide attention of related researchers is attracted, and wind power prediction is a powerful measure and an effective means for solving the problem, so that the wind power prediction becomes one of main research topics in recent years at home and abroad.
At present, a wind power cluster power prediction method comprises an accumulation method and a statistical upscaling method. The cumulative method and the statistical upscaling method have obvious defects, the cumulative method has higher requirements on the completeness of historical data and numerical weather forecast data related to wind power prediction, the calculation is more complex, the time cost is higher, and more data storage resources are needed; the selection of the number of the reference wind power plants and the optimization of the reference wind power plants in the statistical scale-up method have large influence on the prediction accuracy of the total power of the cluster, and simultaneously comprise 2 prediction stages, and the calculation is complex. Therefore, in order to accurately predict the wind power, a relatively simple method with higher prediction precision for optimizing the wind power cluster power prediction parameters is needed.
Disclosure of Invention
The invention aims to provide a method for predicting power and optimizing parameters of a wind power cluster, so as to solve the problems in the background technology.
The purpose of the invention is realized by the following technical measures:
four parameters to be optimized in the method are four parameters of an improved space resource matching method-based wind power cluster power prediction technology in paper 7 of 'Power construction' volume 38, from dminAnd dmedWithin interval intercept close to dminThe percentage of data, namely a scale factor pr, a coefficient alpha to be determined for calculating a distance weight coefficient, a time factor lambda and a power weight coefficient beta for calculating a time weight coefficient, and the specific calculation method and meaning are shown in the content of the paper;
the method is characterized by comprising the following steps:
step 1, dividing historical NWP data and historical power data into two independent data sets of 50% respectively; performing principal component analysis on each 50% of the divided historical NWP data by using original wind speed vectors with different heights, taking the result of the principal component analysis as the input of a wind power cluster power prediction model, dividing 30% of the principal component analysis into a data set to be predicted, dividing the remaining 70% of the principal component analysis into a historical data set, dividing 30% of each 50% of the divided historical power data into a data set to be predicted, and dividing the remaining 70% of the principal component analysis into a historical data set, so that each independent data set is divided into a corresponding data set to be predicted and a corresponding historical data set, and then performing parameter optimization in three stages;
step 2, prediction in the first stage: drawing a scatter distribution diagram by taking the distance of m-dimensional parameters between 2 wind power clusters, namely the space resource distance as an abscissa and the historical power measured value as an ordinate, respectively using each data of a data set to be predicted and a historical data set in each independent data set to calculate the Euclidean characteristic distance between the data set to be predicted and the historical data set, comparing the Euclidean characteristic distance with a threshold delta, thereby obtaining the data set and the predicted data set with the highest matching degree from the historical data set, and weighting and summing to obtain a prediction result;
the calculation method for obtaining the prediction result through weighted summation is shown in formula (1) in section 2.2.1 of 'wind power cluster power prediction technology based on improved space resource matching method' paper in volume 38, No. 7 of the Power construction;
the threshold value delta is calculated by dmin+pr(dmed-dmin)
In the formula: dminIs the minimum distance value among the spatial resource distances, dmedIs the median of the scatter plot, prIs from dminAnd dmedWithin interval intercept close to dminPercentage of data, i.e. scale factor p in four parametersr;
Comparing with a threshold value delta to obtain an overall prediction error value of the data set to be predicted, wherein the data set to be predicted comprises 30% of divided 50% of historical NWP data; judging whether the optimization is finished or not, if the obtained error value is more than 10%, judging that the optimization is not finished, setting parameter values by a variable-scale network search method to continue the optimization, if the obtained error value is less than 10%, judging that the optimization is finished, and comparing four parameters prPrediction accuracy under all combinations of α, λ and β, and four parameters p with minimum overall prediction errorrα, λ and β are initial optimized values;
step 3, second-stage prediction: four parameters p obtained for stage one predictionrControlling the values of three parameters of alpha, lambda and beta to be unchanged, changing the value of the remaining parameter, calculating the Euclidean characteristic distance between a point to be predicted and a historical data set according to the data set to be predicted and the historical data set in the same independent data set, comparing the Euclidean characteristic distance with a threshold value delta to obtain matched data sets, and performing weighted summation on the matched data sets according to the step 2 to obtain a total prediction error; analysis of four parameters prThe influence of alpha, lambda and beta on the prediction accuracy, and respectively combining four parameters prA, lambda and beta pairsAnalyzing the influence rule of the measurement accuracy, and adjusting four parameters p obtained in the first stagerInitial optimized values of α, λ and β, with four parameters p for minimum overall prediction errorrAlpha, lambda and beta as four parameters prOptimal combined values of α, λ and β;
and 4, predicting in a third stage: and setting a key parameter combination optimization value according to the result of the stage two prediction, calculating the Euclidean characteristic distance between the point to be predicted and the historical data set according to the optimization value and the data set to be predicted and the historical data set in the other independent data set, comparing the Euclidean characteristic distance with a threshold value delta, obtaining the data set with the highest matching degree and the predicted data set from the historical data set, and obtaining the prediction result by weighting and summing to obtain the prediction result of each point.
The difference between the application and the paper "wind power cluster power prediction technology based on the improved spatial resource matching method" in the No. 7 article of the 38 th volume of the electric power construction "is the following three points: the application provides a detailed historical data set dividing method; the application provides a unique three-stage prediction optimization process; the present application proposes four key parameters prDetailed optimization procedures of α, λ and β.
The invention achieves the following beneficial effects: a wind power cluster power prediction and parameter optimization method is based on data mining of a large number of samples, and provides a novel multi-feature similarity matching method, and the data mining based on the large number of samples is an effective way for improving wind power prediction precision; through wind power plant cluster verification, the result shows that the improved multi-feature similarity matching method is superior to the traditional prediction method, the root mean square error in 0-2 hours is reduced by 3.65%, and the root mean square error in 0-4 hours is reduced by 1.56%.
Drawings
Fig. 1 is a block diagram of the overall flow structure of the present invention.
Detailed Description
The following detailed description is made with reference to the accompanying drawings in the embodiment of the invention, and the invention aims to provide a wind power cluster power prediction and parameter optimization method for improving wind power prediction accuracy based on data mining of a large number of samples.
As shown in fig. 1, four parameters to be optimized in the method are four parameters of "wind power cluster power prediction technology based on improved spatial resource matching method" in paper No. 7 of "power construction" volume 38, from dminAnd dmedWithin interval intercept close to dminPercentage of data, i.e. scale factor prA to-be-determined coefficient alpha for calculating a distance weight coefficient, a time factor lambda for calculating a time weight coefficient and a power weight coefficient beta, wherein the specific calculation method and meaning are shown in the content of the paper; the method is characterized by comprising the following steps:
step 1, dividing historical NWP data and historical power data into two independent data sets of 50% respectively; performing principal component analysis on each 50% of the divided historical NWP data by using original wind speed vectors with different heights, taking the result of the principal component analysis as the input of a wind power cluster power prediction model, dividing 30% of the principal component analysis into a data set to be predicted, dividing the remaining 70% of the principal component analysis into a historical data set, dividing 30% of each 50% of the divided historical power data into a data set to be predicted, and dividing the remaining 70% of the principal component analysis into a historical data set, so that each independent data set is divided into a corresponding data set to be predicted and a corresponding historical data set, and then performing parameter optimization in three stages;
step 2, prediction in the first stage: drawing a scatter distribution diagram by taking the distance of m-dimensional parameters between 2 wind power clusters, namely the space resource distance as an abscissa and the historical power measured value as an ordinate, respectively using each data of a data set to be predicted and a historical data set in each independent data set to calculate the Euclidean characteristic distance between the data set to be predicted and the historical data set, comparing the Euclidean characteristic distance with a threshold delta, thereby obtaining the data set and the predicted data set with the highest matching degree from the historical data set, and weighting and summing to obtain a prediction result;
the calculation method for obtaining the prediction result through weighted summation is shown in formula (1) in section 2.2.1 of 'wind power cluster power prediction technology based on improved space resource matching method' paper in volume 38, No. 7 of the Power construction;
the threshold value delta is calculated by
δ=dmim+pr(dmed-dmin)
In the formula: dminIs the minimum distance value among the spatial resource distances, dmedIs the median of the scatter plot, prIs from dminAnd dmedWithin interval intercept close to dminPercentage of data, i.e. scale factor p in four parametersr;
Comparing with a threshold value delta to obtain an overall prediction error value of the data set to be predicted, wherein the data set to be predicted comprises 30% of divided 50% of historical NWP data; judging whether the optimization is finished or not, if the obtained error value is more than 10%, judging that the optimization is not finished, setting parameter values by a variable-scale network search method to continue the optimization, if the obtained error value is less than 10%, judging that the optimization is finished, and comparing four parameters prPrediction accuracy under all combinations of α, λ and β, and four parameters p with minimum overall prediction errorrα, λ and β are initial optimized values;
step 3, second-stage prediction: four parameters p obtained for stage one predictionrControlling the values of three parameters of alpha, lambda and beta to be unchanged, changing the value of the remaining parameter, calculating the Euclidean characteristic distance between a point to be predicted and a historical data set according to the data set to be predicted and the historical data set in the same independent data set, comparing the Euclidean characteristic distance with a threshold value delta to obtain matched data sets, and performing weighted summation on the matched data sets according to the step 2 to obtain a total prediction error; analysis of four parameters prThe influence of alpha, lambda and beta on the prediction accuracy, and respectively combining four parameters prAnd the influence rule of alpha, lambda and beta on the prediction precision is analyzed, and four parameters p obtained in the first stage are adjustedrInitial optimized values of α, λ and β, with four parameters p for minimum overall prediction errorrAlpha, lambda and beta as four parameters prOptimal combined values of α, λ and β;
and 4, predicting in a third stage: and setting a key parameter combination optimization value according to the result of the stage two prediction, calculating the Euclidean characteristic distance between the point to be predicted and the historical data set according to the optimization value and the data set to be predicted and the historical data set in the other independent data set, comparing the Euclidean characteristic distance with a threshold value delta, obtaining the data set with the highest matching degree and the predicted data set from the historical data set, and obtaining the prediction result by weighting and summing to obtain the prediction result of each point.
Claims (1)
1. A method for predicting power of a wind power cluster and optimizing parameters is characterized in that four parameters to be optimized in the method are minimum distance values d in space resource distancesminMedian d of the scatter plotmedWithin interval intercept close to dminPercentage of data, i.e. scale factor prThe system comprises a distance weight coefficient, a to-be-determined coefficient alpha for calculating the distance weight coefficient, a time factor lambda for calculating the time weight coefficient and a power weight coefficient beta;
the method is characterized by comprising the following steps:
step 1, dividing historical NWP data and historical power data into two independent data sets of 50% respectively; performing principal component analysis on each 50% of the divided historical NWP data by using original wind speed vectors with different heights, taking the result of the principal component analysis as the input of a wind power cluster power prediction model, dividing 30% of the principal component analysis into a data set to be predicted, dividing the remaining 70% of the principal component analysis into a historical data set, dividing 30% of each 50% of the divided historical power data into a data set to be predicted, and dividing the remaining 70% of the principal component analysis into a historical data set, so that each independent data set is divided into a corresponding data set to be predicted and a corresponding historical data set, and then performing parameter optimization in three stages;
step 2, prediction in the first stage: drawing a scatter distribution diagram by taking the distance of m-dimensional parameters between 2 wind power clusters, namely the space resource distance as an abscissa and the historical power measured value as an ordinate, respectively using each data of a data set to be predicted and a historical data set in each independent data set to calculate the Euclidean characteristic distance between the data set to be predicted and the historical data set, comparing the Euclidean characteristic distance with a threshold delta, thereby obtaining the data set and the predicted data set with the highest matching degree from the historical data set, and weighting and summing to obtain a prediction result;
the calculation method for obtaining the prediction result by weighted summation comprises
In the formula:the predicted value of the wind power cluster power after h hours; n is the number of the matching sets with the highest similarity to the spatial resources at the t + h moment to be predicted; piMatching the measured value of the wind power cluster power in the set for the history; omegai,t+hThe greater the value of the spatial resource similarity, the power of the set at the moment to be predictedThe larger the weight value of the contribution;
the threshold value delta is calculated by
δ=dmin+pr(dmed-dmin)
In the formula: dminIs the minimum distance value among the spatial resource distances, dmedIs the median of the scatter plot, prIs from dminAnd dmedWithin interval intercept close to dminPercentage of data, i.e. scale factor p in four parametersr;
Comparing with a threshold value delta to obtain an overall prediction error value of the data set to be predicted, wherein the data set to be predicted comprises 30% of divided 50% of historical NWP data; judging whether the optimization is finished or not, if the obtained error value is more than 10%, judging that the optimization is not finished, setting parameter values by a variable-scale network search method to continue the optimization, if the obtained error value is less than 10%, judging that the optimization is finished, and comparing four parameters prAll of alpha, lambda and betaPrediction accuracy in combination and four parameters p with minimum overall prediction errorrα, λ and β are initial optimized values;
step 3, second-stage prediction: four parameters p obtained for stage one predictionrControlling the values of three parameters of alpha, lambda and beta to be unchanged, changing the value of the remaining parameter, calculating the Euclidean characteristic distance between a point to be predicted and a historical data set according to the data set to be predicted and the historical data set in the same independent data set, comparing the Euclidean characteristic distance with a threshold value delta to obtain matched data sets, and performing weighted summation on the matched data sets according to the step 2 to obtain a total prediction error; analysis of four parameters prThe influence of alpha, lambda and beta on the prediction accuracy, and respectively combining four parameters prAnd the influence rule of alpha, lambda and beta on the prediction precision is analyzed, and four parameters p obtained in the first stage are adjustedrInitial optimized values of α, λ and β, with four parameters p for minimum overall prediction errorrAlpha, lambda and beta as four parameters prOptimal combined values of α, λ and β;
and 4, predicting in a third stage: and setting a key parameter combination optimization value according to the result of the stage two prediction, calculating the Euclidean characteristic distance between the point to be predicted and the historical data set according to the optimization value and the data set to be predicted and the historical data set in the other independent data set, comparing the Euclidean characteristic distance with a threshold value delta, obtaining the data set with the highest matching degree and the predicted data set from the historical data set, and obtaining the prediction result by weighting and summing to obtain the prediction result of each point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910991503.2A CN111222738B (en) | 2019-10-18 | 2019-10-18 | Method for predicting power and optimizing parameters of wind power cluster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910991503.2A CN111222738B (en) | 2019-10-18 | 2019-10-18 | Method for predicting power and optimizing parameters of wind power cluster |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111222738A CN111222738A (en) | 2020-06-02 |
CN111222738B true CN111222738B (en) | 2022-04-15 |
Family
ID=70830560
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910991503.2A Active CN111222738B (en) | 2019-10-18 | 2019-10-18 | Method for predicting power and optimizing parameters of wind power cluster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111222738B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117937638B (en) * | 2024-03-12 | 2024-07-09 | 山西城市动力新能源有限公司 | Wind power plant cluster power generation control method and device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279804A (en) * | 2013-04-29 | 2013-09-04 | 清华大学 | Super short-period wind power prediction method |
CN106875033A (en) * | 2016-12-26 | 2017-06-20 | 华中科技大学 | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting |
CN108133279A (en) * | 2017-08-29 | 2018-06-08 | 甘肃省电力公司风电技术中心 | Wind power probability forecasting method, storage medium and equipment |
CN108616139A (en) * | 2016-12-12 | 2018-10-02 | 中国电力科学研究院 | A kind of wind power cluster prediction technique and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140336934A1 (en) * | 2013-05-07 | 2014-11-13 | Atomic Energy Council - Institute Of Nuclear Energy Research | Ensemble wind power forecasting platform system and operational method thereof |
-
2019
- 2019-10-18 CN CN201910991503.2A patent/CN111222738B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279804A (en) * | 2013-04-29 | 2013-09-04 | 清华大学 | Super short-period wind power prediction method |
CN108616139A (en) * | 2016-12-12 | 2018-10-02 | 中国电力科学研究院 | A kind of wind power cluster prediction technique and device |
CN106875033A (en) * | 2016-12-26 | 2017-06-20 | 华中科技大学 | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting |
CN108133279A (en) * | 2017-08-29 | 2018-06-08 | 甘肃省电力公司风电技术中心 | Wind power probability forecasting method, storage medium and equipment |
Non-Patent Citations (2)
Title |
---|
基于改进空间资源匹配法的风电集群功率预测技术;彭小圣等;《电力建设》;20170701;第38卷(第7期);第10-17页 * |
风电集群短期及超短期功率预测精度改进方法综述;彭小圣等;《中国电机工程学院》;20161205;第36卷(第23期);第6215-6326页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111222738A (en) | 2020-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108876054B (en) | Short-term power load prediction method based on improved genetic algorithm optimization extreme learning machine | |
CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
CN108009938B (en) | System load clustering and load period pattern recognition method based on shape | |
CN109886465B (en) | Power distribution network load prediction method based on intelligent electric meter user cluster analysis | |
CN108932557A (en) | A kind of Short-term Load Forecasting Model based on temperature cumulative effect and grey relational grade | |
CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
CN105069236B (en) | Consider the broad sense load joint probability modeling method of wind power plant node space correlation | |
CN107679687A (en) | A kind of photovoltaic output modeling method and Generation System Reliability appraisal procedure | |
CN105701562B (en) | Training method, applicable method for predicting generated power and respective system | |
CN104865827B (en) | Oil pumping unit oil extraction optimization method based on multi-working-condition model | |
CN105243461A (en) | Short-term load forecasting method based on artificial neural network improved training strategy | |
CN110852492A (en) | Photovoltaic power ultra-short-term prediction method for finding similarity based on Mahalanobis distance | |
CN110598929A (en) | Wind power nonparametric probability interval ultrashort term prediction method | |
CN114611842B (en) | Whole-county roof distributed photovoltaic power prediction method | |
CN111222738B (en) | Method for predicting power and optimizing parameters of wind power cluster | |
CN113659631B (en) | Wind-solar power station group output description method considering time-varying characteristics | |
CN114123294B (en) | Multi-target photovoltaic single-phase grid-connected capacity planning method considering three-phase unbalance | |
CN109193791B (en) | Wind power convergence tendency state-based quantification method based on improved shape value | |
CN113505909B (en) | Error compensation method for short-term wind power trend prediction | |
CN106960260B (en) | Wind power prediction system convenient for power dispatching | |
CN112348236A (en) | Abnormal daily load demand prediction system and method for intelligent power consumption monitoring terminal | |
Yong et al. | Short-term building load forecasting based on similar day selection and LSTM network | |
CN111353649B (en) | KL expansion-based large-scale hydropower station group optimal scheduling dimension reduction method | |
CN109524983B (en) | Photovoltaic output modeling method based on typical state | |
Meng et al. | Load forecasting method considering temperature effect for distribution network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |