Scholarlink

<p>As a key component of the global transition to clean energy, solar power generation requires highly accurate irradiance forecasting to support grid scheduling, renewable energy utilization, and real-time operational decision-making. To improve the accuracy, robustness, and deployment efficiency of hourly solar irradiance forecasting, this study proposes a new framework, AGCRIME-VMD-BiLSTM-SA. First, a multi-perspective feature selection strategy is adopted to identify the most influential variables from multidimensional meteorological data. Then, Arnold’s cat map is introduced into the RIME algorithm to enhance the diversity of the initial population, while an adaptive Gaussian–Cauchy mixed perturbation is incorporated to strengthen global search capability, forming the AGCRIME algorithm for optimizing the hyperparameters of variational mode decomposition (VMD). Since this parameter-search process involves repeated candidate evaluation and iterative optimization, it is computationally intensive and well suited to parallel acceleration or high-performance computing during model construction. Subsequently, the optimized VMD is used to decompose the original irradiance series into several more stable subsequences, which are further modeled by a bidirectional long short-term memory network with self-attention (BiLSTM-SA) to better capture irradiance fluctuations under complex meteorological disturbances. Experimental results show that the proposed AGCRIME-VMD-BiLSTM-SA model achieves a coefficient of determination (<i>R</i>2) of 0.9969. Compared with RIME-VMD-BiLSTM-SA, the mean absolute error is reduced by 26.29%. In addition, the proposed framework outperforms twelve benchmark models across multiple evaluation metrics. Furthermore, the framework follows an offline–online computational pattern: The AGCRIME-based search is mainly performed offline during the model-building stage, whereas the online stage only requires fixed-parameter VMD decomposition and BiLSTM-SA forward inference. This makes the proposed method relevant to both high-performance computing scenarios and real-time grid-support applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Short-term solar irradiance forecasting based on AGCRIME-optimized VMD decomposition and BiLSTM-SA

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Ziqiong Li,
  • Shengjun Liu,
  • Yun Zhang,
  • Xinru Liu

摘要

As a key component of the global transition to clean energy, solar power generation requires highly accurate irradiance forecasting to support grid scheduling, renewable energy utilization, and real-time operational decision-making. To improve the accuracy, robustness, and deployment efficiency of hourly solar irradiance forecasting, this study proposes a new framework, AGCRIME-VMD-BiLSTM-SA. First, a multi-perspective feature selection strategy is adopted to identify the most influential variables from multidimensional meteorological data. Then, Arnold’s cat map is introduced into the RIME algorithm to enhance the diversity of the initial population, while an adaptive Gaussian–Cauchy mixed perturbation is incorporated to strengthen global search capability, forming the AGCRIME algorithm for optimizing the hyperparameters of variational mode decomposition (VMD). Since this parameter-search process involves repeated candidate evaluation and iterative optimization, it is computationally intensive and well suited to parallel acceleration or high-performance computing during model construction. Subsequently, the optimized VMD is used to decompose the original irradiance series into several more stable subsequences, which are further modeled by a bidirectional long short-term memory network with self-attention (BiLSTM-SA) to better capture irradiance fluctuations under complex meteorological disturbances. Experimental results show that the proposed AGCRIME-VMD-BiLSTM-SA model achieves a coefficient of determination (R2) of 0.9969. Compared with RIME-VMD-BiLSTM-SA, the mean absolute error is reduced by 26.29%. In addition, the proposed framework outperforms twelve benchmark models across multiple evaluation metrics. Furthermore, the framework follows an offline–online computational pattern: The AGCRIME-based search is mainly performed offline during the model-building stage, whereas the online stage only requires fixed-parameter VMD decomposition and BiLSTM-SA forward inference. This makes the proposed method relevant to both high-performance computing scenarios and real-time grid-support applications.