Feature extraction of meteorological factors for wind power prediction based on variable weight combined method

Lu, Peng; Ye, Lin; Zhao, Yongning; Dai, Binhua; Pei, Ming; Li, Zhuo

doi:10.1016/j.renene.2021.08.007

Cited by 41 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[205] Longterm forecasting is typically used for optimal designing of a wind farm and energy marketing. [206,207] The correlation between actual power values and prediction values plays a significant role in terms of accuracy, [208] reliability, [209] and sharpness. [210] The accuracy determines the qualification of WPF and varies according to the timescale and methodology.…”

Section: Observing and Trackingmentioning

confidence: 99%

A Review on Wind Power Forecasting Regarding Impacts on the System Operation, Technical Challenges, and Applications

et al. 2022

View full text Add to dashboard Cite

Wind energy generation is a fast developing efficient renewable source widely used for modern power generation. [1] Countries and energy companies have increased their interest in electricity generation from wind energy in the last decades, thanks to its natural, cost-free, and environmentally friendly features. [2] Wind power plants can generate electrical energy at any time of the day and are distributed energy sources for systems that need permanent energy. [3] Nonetheless, due to the disordered nature of the earth's atmosphere, there is a major uncertainty in the electrical power produced by the wind, which causes complexities in the utilization and management of wind energy sources. [4] The changes in weather conditions depending on time and location also create uncertainty in managing the supply-demand balance controlled by the grid operators. [5] In cases where the electrical energy produced by wind power plants is insufficient, auxiliary energy sources provide operational support to the electric grid. [6] Ensuring the supply-demand balance in the electricity grid is also an important condition for the electrical power quality and energy supply in the transmission system, and wind power plant operators care about the follow-up of wind power in terms of economy, operation, and planning. [7] For this, the presence of wind power forecasting (WPF) is an essential factor in the optimization of wind power plants. [8] For consumers to use electrical energy uninterruptedly, efficiently, and economically, wind power plant operators need to estimate the generated electrical energy smoothly. [9] The smooth estimation of electrical power generated by wind turbines increases the operational efficiency for system maintenance, planning, investment, and energy traders. [10,11] It is a precious procedure for electrical grids to provide a respectable commercial yield on the electrical energy market. [12] The capability of advanced WPF provides the contributions like balancing the power system and mitigation of penalties, scheduling the maintenance of wind power plants, investment regarding site location, and technoeconomic and socioeconomic benefits. [13,14] In this way, it is possible to reduce the energy cost and obtain high revenue in the energy market as a result of the contributions obtained for wind power generation systems. [15]

show abstract

Section: Observing and Trackingmentioning

confidence: 99%

A Review on Wind Power Forecasting Regarding Impacts on the System Operation, Technical Challenges, and Applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffi ffiffi P N i¼1 ½ðy i a À y i p Þ=y nom � 2 q Suitable for multi-objective evaluation with small variance [57].…”

Section: Mean Absolute Percentageunclassified

Active power control strategy for wind farms based on power prediction errors distribution considering regional data

et al. 2022

View full text Add to dashboard Cite

One of the renewable energy resources, wind energy is widely used due to its wide distribution, large reserves, green and clean energy, and it is also an important part of large-scale grid integration. However, wind power has strong randomness, volatility, anti-peaking characteristics, and the problem of low wind power prediction accuracy, which brings serious challenges to the power system. Based on the difference of power prediction error and confidence interval between different new energy power stations, an optimal control strategy for active power of wind farms was proposed. Therefore, we focus on solving the problem of wind power forecasting and improving the accuracy of wind power prediction. Due to the prediction error of wind power generation, the power control cannot meet the control target. An optimal control strategy for active power of wind farms is proposed based on the difference in power prediction error and confidence interval between different new energy power stations. The strategy used historical data to evaluate the prediction error distribution and confidence interval of wind power. We use confidence interval constraints to create a wind power active optimization model that realize active power distribution and complementary prediction errors among wind farms with asymmetric error distribution. Combined with the actual data of a domestic (Cox’s Bazar, Bangladesh) wind power base, a simulation example is designed to verify the rationality and effectiveness of the proposed strategy.

show abstract

“…To solve the problem of nonstationary signals influenced by wind speed, Jiajun et al proposed the method of wavelet decomposition and reconstruction, 21 Wang et al adopted the method of empirical mode decomposition (EMD) to transform the original signal into a relatively stationary signal 22 . Lu used feature extraction technology to extract features of NWP and historical wind power data, designed predictors based on extreme learning machine (ELM) and least square support vector machine (LSSVM) models, and then used improved cuckoo search (ICS) to predict key parameters of the model optimize 23 . To improve the accuracy of ultra‐short‐term wind power prediction, Liu uses a combination of variational mode decomposition (VMD) and long short‐term memory (LSTM) networks for prediction 24 .…”

Section: Introductionmentioning

confidence: 99%

“…22 Lu used feature extraction technology to extract features of NWP and historical wind power data, designed predictors based on extreme learning machine (ELM) and least square support vector machine (LSSVM) models, and then used improved cuckoo search (ICS) to predict key parameters of the model optimize. 23 To improve the accuracy of ultra-short-term wind power prediction, Liu uses a combination of variational mode decomposition (VMD) and long short-term memory (LSTM) networks for prediction. 24 Although these methods improved the prediction accuracy of the model to some extent, they did not depict the motion law of the disturbance factor fundamentally.…”

Section: Introductionmentioning

confidence: 99%

Forecasting ultra‐short‐term wind power by multiview gated recurrent unit neural network

Xiong

Cai

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

Wind power generation prediction plays an important role in the safety and economic operation of the power system. There are many parameters recorded in wind farm data, such as wind power, wind speed, wind direction, and so on. Traditional wind power prediction modeling methods lack the mining of these parameter data and fail to make good use of some potential physical information. To address this challenge, this paper proposes a multiview neural network learning framework to predict wind power. One is the data attribute view of wind power, which uses the historical data feature of the wind power itself to learn the future wind power feature. The other is the physical attribute view of wind power, which uses the physical attribute features associated with the wind power definition to learn the future features. Then all the learned features are jointly fused to predict the future wind power values. In addition, an uncertain factor is proposed and computed, which is inspired by the wind power formula and usually associated with internal and external environment perturbation. All time series features are input into the gated recurrent unit neural network to form a hybrid neural network framework for wind power prediction. Experimental results under the measured condition and the standard condition of wind farms demonstrate the effectiveness of the proposed method.

show abstract

Feature extraction of meteorological factors for wind power prediction based on variable weight combined method

Cited by 41 publications

References 44 publications

A Review on Wind Power Forecasting Regarding Impacts on the System Operation, Technical Challenges, and Applications

A Review on Wind Power Forecasting Regarding Impacts on the System Operation, Technical Challenges, and Applications

Active power control strategy for wind farms based on power prediction errors distribution considering regional data

Forecasting ultra‐short‐term wind power by multiview gated recurrent unit neural network

Contact Info

Product

Resources

About