Answers are grounded in this paper and cite their sources.
Novel hybrid model improves accuracy of short-term load forecasting using two-phase decomposition and spectral entropy.
Short-term load forecasting is essential for power system stability and resource optimization, but existing methods struggle with load randomness and complexity, resulting in low accuracy. This paper proposes a novel two-phase decomposition-based hybrid forecasting model that integrates Successive Variational Mode Decomposition (SVMD), Spectral Entropy, Ensemble Empirical Mode Decomposition (EEMD), and R-Informer. The proposed method first employs SVMD to decompose the load sequence into multiple intrinsic mode functions (IMFs) of different frequencies. Then, the spectral entropy of each IMF is calculated. The IMF with the highest spectral entropy is further decomposed using EEMD method. This technique yields a set of stationary components. Furthermore, this paper proposes an Adaptive Recursive Cycle (ARC) mechanism, which utilizes learnable periodic embeddings and exponential moving average (EMA) to adaptively model periodic patterns. The ARC mechanism enhances periodic information representation through linear transformation. Based on this, this paper proposes the R-Informer model, which integrates ARC and Informer to predict the decomposed components. Experimental results demonstrate that the proposed forecasting model effectively handles non-stationary load sequences and achieves high accuracy in short-term power load forecasting.
No takes yet. Share an insight, caveat, or question.
Ding et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: