Hybrid Decomposition-Reconfiguration Models for Long-Term Solar Radiation Prediction Only Using Historical Radiation Records

Abstract

Solar radiation prediction is significant for solar energy utilization. This paper presents hybrid methods following the decomposition-prediction-reconfiguration paradigm using only historical radiation records with different combination of decomposition methods, Ensemble Empirical Mode Decomposition (EEMD) and Wavelet Analysis (WA), and the reconfiguration methods, regression model (RE) and Artificial Neural Network (ANN). The application in west China indicates that these hybrid decomposition-reconfiguration models perform well for monthly prediction, while the comparisons of the daily prediction show that the hybrid EEMD-RE model has a higher degree of fitting and a better prediction effect in long-term prediction of solar radiation intensity, which verifies (1) decomposition of original solar radiation data results in components with regular characteristics; (2) the relationship between the original solar radiation sequence and the derived intrinsic mode functions (IMFs) is linear; and (3) EEMD has strong adaptivity for non-linear and non-stationary series. The proposed hybrid decomposition-reconfiguration models have great application prospect for monthly long-term prediction of solar radiation intensity, especially in the areas where complex climate data is difficult to obtain, and the EEMD-RE model is recommended for the daily long-term prediction.

Fast Univariate Time Series Prediction of Solar Power for Real-Time Control of Energy Storage System

“…Univariate model-based methods can be divided into linear models, mainly including autoregressive and autoregressive moving average models [13], and nonlinear models such as artificial neural networks [14], support vector machine with kernel trick [15], decision tree [16], wavelet-based methods [17], Markov regime switching model [18], and k-nearest neighbors (kNN) [16]. Although nonlinear models (compared to linear models) seem to be more accurate in terms of capturing the nonlinear characteristic and time varying behavior of solar power generation, these methods generally take a longer time for training/tuning parameters and easily fall into local minimum.…”

“…Although a limited number of publications in the literature put emphasis on the super-short-term prediction timeframe, this type of prediction is useful for real time control of renewables, regulation actions and power quality enhancement. Short-term prediction methods are suitable for economic load dispatch planning or load increment/decrement decisions, and long-term prediction is normally valuable for unit commitment decisions, reserve requirement decisions, and maintenance scheduling to obtain optimal operating cost [17]. In Ref.…”

“…The objective of the latter paper is to predict one step-ahead solar power generation (minutely) based only on historical solar power time series data. Long-term solar prediction is investigated in Ref [17]; it develops a 1-day-ahead forecasting model based on an artificial neural network with tapped delay lines. In Ref.…”

Hybrid Approach of Fractional Generalized Pareto Motion and Cosine Similarity Hidden Markov Model for Solar Radiation Forecasting

“…Meteorological quantities are stable in a site with photovoltaic panels. Therefore, training the model from the historical effective daily surface radiation has significant importance for the forecasting of solar irradiation [9].…”

Decomposition-Based Multi-Step Forecasting Model for the Environmental Variables of Rabbit Houses

“…The multivariate and multi-step time series forecasting model's input-output mapping is quite complex and has a low prediction accuracy. To effectively carry out long sequence prediction by fully mining the dependence relationship between time series, researchers have proposed various models based on mathematical transformations [28], Temporal Convolutional Network [29], and Ensemble Empirical Mode Decomposition [30]. Informer [31], a long series forecasting model based on the attention mechanism proposed in 2021, effectively extracts the coupling relationship between the correlated time series through the complex nonlinear mapping relationship established by the encoder and decoder, reduces computational complexity by using the sparse self-attention mechanism, and predicts the correlated time series accurately and efficiently.…”