Point and Interval Solar Power Forecasting Using Hybrid Empirical Wavelet Transform and Robust Wavelet Kernel Ridge Regr
- PDF / 2,551,048 Bytes
- 29 Pages / 595.276 x 790.866 pts Page_size
- 76 Downloads / 179 Views
Original Paper
Point and Interval Solar Power Forecasting Using Hybrid Empirical Wavelet Transform and Robust Wavelet Kernel Ridge Regression P. K. Dash,1 Irani Majumder,1 Niranjan Nayak,1 and Ranjeeta Bisoi1,2 Received 21 June 2019; accepted 31 January 2020
In this paper, a new and efficient hybrid empirical wavelet transform (EWT)-based reduced robust Mexican hat wavelet kernel ridge regression (RMHWK) model is proposed to achieve both point and interval forecasting of solar power in a smart grid scenario. Initially, the actual nonlinear solar power data series was decomposed by the EWT method. A reduced robust kernel ridge regression (RKRR) approach was incorporated that shows a notable decrease in training time without appreciable loss in forecasting accuracy. The reduction in the size of the kernel matrix was achieved by selecting a set of random support vectors from the training data set. For validating the superior performance of the proposed EWT-RMHWK forecasting model, a numerical experimentation implementing a real-time data set of 1 MW solar power plant (Odisha, India) as well as an online historical data set (Florida, USA) was considered and compared with other hybrid models using either empirical mode decomposition- or wavelet decomposition-based RKRR and EWT-ELM, etc. The kernel parameters were optimized with the chaotic water cycle algorithm to boost the performance of the proposed prediction model. Further, the proposed EWT-RKRR method was used to construct prediction interval forecasting with three different confidence levels with 90%, 95%, and 99% for Florida solar power plant using different time horizons of 15 min, 1 h, and 1 day, respectively. KEY WORDS: Empirical wavelet transform (EWT), Empirical mode decomposition (EMD), Wavelet decomposition (WD), Robust kernel ridge regression (RKRR), Prediction interval (PI), Chaotic water cycle optimization technique (CWCA).
INTRODUCTION Motivation With the increase in energy demand and depletion of conventional energy resources, solar energy has assumed importance globally because of its clean nature and wide availability. In addition, 1
Siksha O Anusandhan (Deemed to be University), Bhubaneswar, India. 2 To whom correspondence should be addressed; e-mail: [email protected]
the solar energy has experienced notable growth due to its high penetration in the smart grid operation (Steffel et al. 2012). However, the stochastic nature of PV generation introduces significant challenges in the smart grid energy management like the system stability, electrical power balance, reactive power requirement, system frequency disturbances (Yang et al. 2013; Shah et al. 2015; Ueckerdt et al. 2015), etc. Precise prediction of solar power generation plays an important role in micro-grid energy management system by improving the power quality while reducing the cost (Yang et al. 2014). It also
2020 International Association for Mathematical Geosciences
Dash, Majumder, Nayak, and Bisoi allows efficient planning and sizing of PV power plants, resulting in an
Data Loading...
