Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model

By Zhen-hai Guo, Weigang Zhao, Haiyan Helen Lu, Jianzhou Wang. 2012

510 citations recorded by the source corpus.

In this paper, a modified EMD-FNN model (empirical mode decomposition (EMD) based feed-forward neural network (FNN) ensemble learning paradigm) is proposed for wind speed forecasting. The nonlinear and non-stationary original wind speed series is first decomposed into a finite and often small number of intrinsic mode functions (IMFs) and one residual series using EMD technique for a deep insight into the data structure. Then these sub-series except the high frequency are forecasted respectively by FNN whose input variables are selected by using partial autocorrelation function (PACF). Finally, the prediction results of the modeled IMFs and residual series are summed to formulate an ensemble forecast for the original wind speed series. Further more, the developed model shows the best accuracy comparing with basic FNN and unmodified EMD-based FNN through multi-step forecasting the mean monthly and daily wind speed in Zhangye of China.

Subfields: Control and Systems Engineering, Electrical and Electronic Engineering, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/cb9b7caf482d4853206f57fb38009679bb38c2d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Tzu-Yu Lin
2. Sheng-Hsiung Chiu
3. Katya Scheinberg
4. Yi-Ming Wei
5. Frank E. Curtis
6. Robert P. Broadwater
7. Chiun-Sin Lin
8. Jaesung Jung

In Electrical and Electronic Engineering

1. Zhang Tao
2. Yi-Ming Wei
3. Frank E. Curtis
4. Robert P. Broadwater
5. Jaesung Jung

In Management Science and Operations Research

1. Katya Scheinberg
2. Yi-Ming Wei
3. Tzu-Yu Lin
4. Zhang Tao
5. Sheng-Hsiung Chiu
6. Frank E. Curtis
7. Robert P. Broadwater
8. Chiun-Sin Lin

Citations in the corpus

• Current status and future advances for wind speed and power forecasting (2014, methodology): “In [56], standard multi-layer Feed-forward Neural Network (FNN) is employed to forecast the wind speed.”
• Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression (2017, methodology): “Consequently, 25 Inspired by Tang et al. (2012)[18], Guo et al. (2012)[28], Zhu and Wei,(2013)[10] and Yu et al. (2015)[39], two single 26 models (LSSVR and ARIMA), a hybrid ARIMA+LSSVR model, and four multiscale forecasting models (EMD–27 ARIMA–IMF1–ADD, EMD–ARIMA–ADD, EMD–LSSVR–IMF1–ADD and…”
• Wind Speed Interval Prediction Based on Lorenz Disturbance Distribution (2020, methodology): “Interval prediction is based on the point prediction, the commonly used prediction model include time series model [2], [3], neural network model [4], [5], support vector machine model [6], [7], [41] and so on.”
• Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning (2017, background): “…helped to train DNNs for large-scale applications, such as for speech recognition [40, 35], image classification [18, 47, 77], human action recognition [43], video classification [45], forecasting [56, 36, 81, 83], machine translation [17, 2], and civil engineering [26, 1, 46, 24]; see also [89].”
• Empirical mode decomposition–based least squares support vector regression for foreign exchange rate forecasting (2012, methodology): “Guo et al. (2012), for example, decomposed wind-speed series using EMD and then forecasted them using a feed-forward neural network, whereas Chen et al. (2012) proposed an EMD approach combined with an artificial neural network for tourism-demand forecasting.”