A Hybrid Forecasting Method for Solar Output Power Based on Variational Mode Decomposition, Deep Belief Networks and Auto-Regressive Moving Average

Tuo Xie,Fuchao Liu,Peidong Du,Hongchi Liu,Gang Zhang

doi:10.3390/app8101901

Tuo Xie, Fuchao Liu + Show 3 more

Open Access

https://doi.org/10.3390/app8101901

Copy DOI

Abstract

Due to the existing large-scale grid-connected photovoltaic (PV) power generation installations, accurate PV power forecasting is critical to the safe and economical operation of electric power systems. In this study, a hybrid short-term forecasting method based on the Variational Mode Decomposition (VMD) technique, the Deep Belief Network (DBN) and the Auto-Regressive Moving Average Model (ARMA) is proposed to deal with the problem of forecasting accuracy. The DBN model combines a forward unsupervised greedy layer-by-layer training algorithm with a reverse Back-Projection (BP) fine-tuning algorithm, making full use of feature extraction advantages of the deep architecture and showing good performance in generalized predictive analysis. To better analyze the time series of historical data, VMD decomposes time series data into an ensemble of components with different frequencies; this improves the shortcomings of decomposition from Empirical Mode Decomposition (EMD) and Ensemble Empirical Mode Decomposition (EEMD) processes. Classification is achieved via the spectrum characteristics of modal components, the high-frequency Intrinsic Mode Functions (IMFs) components are predicted using the DBN, and the low-frequency IMFs components are predicted using the ARMA. Eventually, the forecasting result is generated by reconstructing the predicted component values. To demonstrate the effectiveness of the proposed method, it is tested based on the practical information of PV power generation data from a real case study in Yunnan. The proposed approach is compared, respectively, with the single prediction models and the decomposition-combined prediction models. The evaluation of the forecasting performance is carried out with the normalized absolute average error, normalized root-mean-square error and Hill inequality coefficient; the results are subsequently compared with real-world scenarios. The proposed approach outperforms the single prediction models and the combined forecasting methods, demonstrating its favorable accuracy and reliability.

Highlights

To promote sustainable economic and social development, energy sources such as solar energy and wind power need to be leveraged to counteract the rapidly growing energy consumption and deteriorating environment caused by climate change
The short-term prediction accuracy of the nonlinear PV power time series in this work proposes a multi-frequency combined prediction model based on Variational Mode Decomposition (VMD) mode decomposition
A combination method based on VMD-Auto-Regressive Moving Average Model (ARMA)-Deep Belief Network (DBN) is proposed, which reflects the development trend of the size of PV output, and decomposes the fluctuation series into a set of less complex and some strong periodical parameters, which greatly reduced the difficulty of prediction

Summary

Introduction

To promote sustainable economic and social development, energy sources such as solar energy and wind power need to be leveraged to counteract the rapidly growing energy consumption and deteriorating environment caused by climate change. To promote increased solar energy utilization, photovoltaic (PV) power generation has been rapidly developed worldwide [1]. Sci. 2018, 8, 1901 is affected by solar radiation, temperature and other factors. Accurate PV power prediction provides the basis for grid dispatch decision-making behavior, and provides support for multiple power source space-time complementarity and coordinated control; this reduces pre-existing rotating reserve capacity and operating costs, which ensures the safety and stability of the system and promotes the optimal operation of the power grid [2]

Methods

Results

Conclusion