Scholarlink

<p>Accurate short-term photovoltaic (PV) power forecasting is increasingly important for maximizing on-site self-consumption and ensuring reliable grid integration as decentralized PV deployment grows. This paper presents a&#xa0;systematic comparison of Long Short-Term Memory (LSTM) and transformer-based architectures for deterministic short-term PV power forecasting using publicly accessible data from multiple climatic regions. The dataset combines multi-year 15-minute PV power measurements from nine plants with corresponding meteorological variables, and it is followed by a&#xa0;unified preprocessing pipeline that includes outlier treatment, interpolation, feature scaling, and correlation-based feature selection. Several feature subsets and input window lengths are evaluated, and Bayesian hyperparameter optimization is employed to refine model configurations for both architectures. The results indicate that using all meteorological variables except cloud coverage with a&#xa0;2-day input window yields the best performance. Under this configuration, the transformer model outperforms the LSTM model, achieving on average test errors of MSE = 0.0038 and MAE = 0.0265, compared to 0.0055 and 0.0343 for the LSTM, respectively. An analysis of time-resolved residuals shows that both models exhibit the largest errors around noon, while the transformer provides a&#xa0;consistently narrower error distribution over the diurnal cycle. These findings highlight the advantages of attention-based sequence modeling for PV applications and offer practical guidance on feature design, input horizon selection, and hyperparameter ranges for future data-driven PV forecasting studies.</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

Residential photovoltaic generation forecast via long short-term memory and transformer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月17日

查看全文
  • Marcel Lüdecke,
  • Elias Oppermann,
  • Michel Meinert,
  • Bernd Engel

摘要

Accurate short-term photovoltaic (PV) power forecasting is increasingly important for maximizing on-site self-consumption and ensuring reliable grid integration as decentralized PV deployment grows. This paper presents a systematic comparison of Long Short-Term Memory (LSTM) and transformer-based architectures for deterministic short-term PV power forecasting using publicly accessible data from multiple climatic regions. The dataset combines multi-year 15-minute PV power measurements from nine plants with corresponding meteorological variables, and it is followed by a unified preprocessing pipeline that includes outlier treatment, interpolation, feature scaling, and correlation-based feature selection. Several feature subsets and input window lengths are evaluated, and Bayesian hyperparameter optimization is employed to refine model configurations for both architectures. The results indicate that using all meteorological variables except cloud coverage with a 2-day input window yields the best performance. Under this configuration, the transformer model outperforms the LSTM model, achieving on average test errors of MSE = 0.0038 and MAE = 0.0265, compared to 0.0055 and 0.0343 for the LSTM, respectively. An analysis of time-resolved residuals shows that both models exhibit the largest errors around noon, while the transformer provides a consistently narrower error distribution over the diurnal cycle. These findings highlight the advantages of attention-based sequence modeling for PV applications and offer practical guidance on feature design, input horizon selection, and hyperparameter ranges for future data-driven PV forecasting studies.