Short-Term PV Power Prediction Based on Optimized VMD and LSTM

Because of intermittence and fluctuation of photovoltaic (PV) power, it is difficult to enhance prediction accuracy. To sustain high-efficient operation of power system, this paper proposes a hybrid method to predict the short-term PV power. It consists of components separation of PV power, parameters optimization and re-construction of prediction result. Firstly, the methods based on the identifying of feature frequency and mutual information maximum are proposed to optimize the mode number and penalty factor of VMD, respectively. The optimized VMD (OVMD) is used to decompose the complicated fluctuation components of PV power into single component. Then, the improved PSO (IPSO) based on non-linear inertia weight of anti-sine function is proposed to optimize the number of hidden layer nodes, learning rate and iteration number of LSTM network. The optimized LSTM is used to predict each single component of OVMD decomposition. Thirdly, the prediction result of each single component is re-constructed to obtain the final PV prediction power. The experiment result indicates that the prediction accuracy of the proposed method (OVMD-IPSO-LSTM) outperformances the other typical methods. By the improvement of the traditional method (VMD and PSO) and the parameter optimization of LSTM, this hybrid method makes a contribution to the prediction of short-term PV power.

[1]  Wen-Chung Shen,et al.  Low-complexity sinusoidal-assisted EMD (SAEMD) algorithms for solving mode-mixing problems in HHT , 2014, Digit. Signal Process..

[2]  Patrick Flandrin,et al.  A complete ensemble empirical mode decomposition with adaptive noise , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Jiakai Ding,et al.  Gear Fault Diagnosis Based on Genetic Mutation Particle Swarm Optimization VMD and Probabilistic Neural Network Algorithm , 2020, IEEE Access.

[4]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  Fang-Fang Li,et al.  Long term rolling prediction model for solar radiation combining empirical mode decomposition (EMD) and artificial neural network (ANN) techniques , 2018 .

[7]  Luca Maria Gambardella,et al.  Ant Algorithms for Discrete Optimization , 1999, Artificial Life.

[8]  Xiaoming Xue,et al.  An adaptively fast ensemble empirical mode decomposition method and its applications to rolling element bearing fault diagnosis , 2015 .

[9]  Junqiang Wang,et al.  Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model , 2020 .

[10]  Daming Xu,et al.  Optimal sizing of standalone hybrid wind/PV power systems using genetic algorithms , 2005, Canadian Conference on Electrical and Computer Engineering, 2005..

[11]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Junichi Murata,et al.  Daily solar radiation prediction based on wavelet analysis , 2011, SICE Annual Conference 2011.

[14]  Jiandong Zhao,et al.  Lane Work-Schedule of Toll Station Based on Queuing Theory and PSO-LSTM Model , 2020, IEEE Access.

[15]  Yan Li,et al.  Daily Peak Load Forecasting Based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Support Vector Machine Optimized by Modified Grey Wolf Optimization Algorithm , 2018 .

[16]  Li Sun,et al.  Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations , 2020, Renewable Energy.

[17]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[18]  Tao Li,et al.  Particle swarm optimizer with crossover operation , 2018, Eng. Appl. Artif. Intell..

[19]  Mohammadamin Azimi,et al.  Carbon trading volume and price forecasting in China using multiple machine learning models , 2020 .

[20]  A. Rezaee Jordehi,et al.  Parameter selection in particle swarm optimisation: a survey , 2013, J. Exp. Theor. Artif. Intell..

[21]  Yukun Wang,et al.  Hybrid quantum particle swarm optimization algorithm and its application , 2019, Science China Information Sciences.

[22]  P. Kundur.  Sustainable electric power systems in the 21st century: requirements, challenges and the role of new technologies , 2004, IEEE Power Engineering Society General Meeting, 2004..

[23]  Zhao Zhen,et al.  A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework , 2020 .

[24]  Haifeng Zhang,et al.  Short-Term Wind Speed Prediction Based on Principal Component Analysis and LSTM , 2020, Applied Sciences.

[25]  Yanping Bai,et al.  Denoising and Baseline Drift Removal Method of MEMS Hydrophone Signal Based on VMD and Wavelet Threshold Processing , 2019, IEEE Access.

[26]  Niranjan Nayak,et al.  Short term PV power forecasting using empirical mode decomposition based orthogonal extreme learning machine technique , 2018 .

[27]  Ram Bilas Pachori,et al.  Automated glaucoma detection using quasi-bivariate variational mode decomposition from fundus images , 2019, IET Image Process..

[28]  Xiaohui Gu,et al.  Improved PSO Algorithm Based on Exponential Center Symmetric Inertia Weight Function and Its Application in Infrared Image Enhancement , 2020, Symmetry.

[29]  Frank Ortmeier,et al.  Independent Analysis of Decelerations and Resting Periods through CEEMDAN and Spectral-Based Feature Extraction Improves Cardiotocographic Assessment , 2019 .

[30]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[31]  Wei Liu,et al.  A Novel Hydrocarbon Detection Approach via High-Resolution Frequency-Dependent AVO Inversion Based on Variational Mode Decomposition , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Chengwei Li,et al.  A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating , 2017 .

[33]  Li,et al.  Short-Term Forecasting of Power Production in a Large-Scale Photovoltaic Plant Based on LSTM , 2019, Applied Sciences.

[34]  Ting-Yu Chen,et al.  On the improvements of the particle swarm optimization algorithm , 2010, Adv. Eng. Softw..

[35]  Arielle Moro,et al.  A Framework to Predict Consumption Sustainability Levels of Individuals , 2020 .

[36]  Henrik Madsen,et al.  Online short-term solar power forecasting , 2009 .

[37]  Rob J Hyndman,et al.  25 years of time series forecasting , 2006 .

[38]  Mohd Yamani Idna Idris,et al.  SVR-Based Model to Forecast PV Power Generation under Different Weather Conditions , 2017 .

[39]  Kashem M. Muttaqi,et al.  A novel control strategy to mitigate slow and fast fluctuations of the voltage profile at common coupling Point of rooftop solar PV unit with an integrated hybrid energy storage system , 2018, Journal of Energy Storage.

[40]  Nima Amjady,et al.  Effective prediction model for Hungarian small-scale solar power output , 2017 .

[41]  Ping-Huan Kuo,et al.  Multiple-Input Deep Convolutional Neural Network Model for Short-Term Photovoltaic Power Forecasting , 2019, IEEE Access.

[42]  Gang Zhang,et al.  A Hybrid Forecasting Method for Solar Output Power Based on Variational Mode Decomposition, Deep Belief Networks and Auto-Regressive Moving Average , 2018, Applied Sciences.

[43]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[44]  Xin He,et al.  LLR: Learning learning rates by LSTM for training neural networks , 2020, Neurocomputing.

[45]  Hongkun Li,et al.  Early Fault Diagnosis for Planetary Gearbox Based on Adaptive Parameter Optimized VMD and Singular Kurtosis Difference Spectrum , 2019, IEEE Access.

[46]  Chengwei Li,et al.  Friction Signal Denoising Using Complete Ensemble EMD with Adaptive Noise and Mutual Information , 2015, Entropy.

[47]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[48]  Yanyang Zi,et al.  Independence-oriented VMD to identify fault feature for wheel set bearing fault diagnosis of high speed locomotive , 2017 .

[49]  Yan Tian,et al.  LSTM-based traffic flow prediction with missing data , 2018, Neurocomputing.

[50]  Enfang Sang,et al.  Analysis and Solution to the Mode Mixing Phenomenon in EMD , 2008, 2008 Congress on Image and Signal Processing.