Scholarlink

<p>With the rapid development of renewable energy, photovoltaic power generation has become a key part of the global energy transition. Short-term photovoltaic prediction is critical for intra-day real-time power grid dispatching, and enhancing its accuracy is a key research focus. However, existing methods still have limitations in handling complex nonlinear relationships in photovoltaic temporal data. To tackle this, this paper proposes a new model combining Long Short-Term Memory (LSTM), Differential Transformer (DiffTransformer), and Multi-Objective Escape Algorithm (MOESC) for short-term photovoltaic power prediction optimization: Preprocessed data is input into the LSTM-Differential Transformer model, with the Differential Transformer encoder capturing fine-grained temporal changes via optimized multi-head attention and rotary positional encoding, and the LSTM decoder integrating local temporal information for power prediction. Subsequently, Pareto-improved MOESC performs multi-objective optimization on the model’s key parameters (balancing <i>RMSE</i>, <i>MAE</i>, and <i>R²</i>), with the optimal parameters selected from the Pareto frontier. Experiments based on the Guoneng Rixin photovoltaic dataset show that, with user-defined weights (<i>RMSE</i>: 30%, <i>MAE</i>: 30%, <i>R²</i>: 40%), this method outperforms XGBoost, LightGBM, SVR, LSTM, GRU and the unoptimized LSTM-Differential Transformer model in photovoltaic power prediction. It not only can effectively improve prediction accuracy but also exhibits better stability compared with the unoptimized LSTM-Differential Transformer model.</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

A method for short-term photovoltaic power prediction integrating long short-term memory network, differential transformer, and multi-objective escape algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月19日

查看全文
  • Yi Zhang,
  • Guangde Zhang,
  • Zengwei Li,
  • Hongkai Zhao,
  • Yuanming Ma,
  • Guodong Li,
  • Rongfu Zhang

摘要

With the rapid development of renewable energy, photovoltaic power generation has become a key part of the global energy transition. Short-term photovoltaic prediction is critical for intra-day real-time power grid dispatching, and enhancing its accuracy is a key research focus. However, existing methods still have limitations in handling complex nonlinear relationships in photovoltaic temporal data. To tackle this, this paper proposes a new model combining Long Short-Term Memory (LSTM), Differential Transformer (DiffTransformer), and Multi-Objective Escape Algorithm (MOESC) for short-term photovoltaic power prediction optimization: Preprocessed data is input into the LSTM-Differential Transformer model, with the Differential Transformer encoder capturing fine-grained temporal changes via optimized multi-head attention and rotary positional encoding, and the LSTM decoder integrating local temporal information for power prediction. Subsequently, Pareto-improved MOESC performs multi-objective optimization on the model’s key parameters (balancing RMSE, MAE, and R²), with the optimal parameters selected from the Pareto frontier. Experiments based on the Guoneng Rixin photovoltaic dataset show that, with user-defined weights (RMSE: 30%, MAE: 30%, R²: 40%), this method outperforms XGBoost, LightGBM, SVR, LSTM, GRU and the unoptimized LSTM-Differential Transformer model in photovoltaic power prediction. It not only can effectively improve prediction accuracy but also exhibits better stability compared with the unoptimized LSTM-Differential Transformer model.