Scholarlink

<p>The rising share of renewable energy has amplified electricity price volatility, underscoring the need for accurate forecasting and robust risk management. This study proposes an integrated machine learning framework that combines advanced forecasting models (Random Forest, XGBoost, LSTM) with feature engineering and probabilistic risk assessment. Value at risk (VaR) and conditional VaR (CVaR) are derived from predictive distributions to guide hedging strategies using futures and options. Empirical tests on 3 years of hourly data show that the approach reduces RMSE by up to 18% and lowers MAPE below 5%, while improving downside protection by 12% compared with benchmarks. The key contributions are the unification of ML forecasting and economic risk measures, demonstrable gains in both accuracy and resilience, and practical guidance for stakeholders in renewable-intensive markets.</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

Machine learning-based price forecasting and risk management in renewable energy markets

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月1日

查看全文
  • Kuochun Lin,
  • Peichun Feng

摘要

The rising share of renewable energy has amplified electricity price volatility, underscoring the need for accurate forecasting and robust risk management. This study proposes an integrated machine learning framework that combines advanced forecasting models (Random Forest, XGBoost, LSTM) with feature engineering and probabilistic risk assessment. Value at risk (VaR) and conditional VaR (CVaR) are derived from predictive distributions to guide hedging strategies using futures and options. Empirical tests on 3 years of hourly data show that the approach reduces RMSE by up to 18% and lowers MAPE below 5%, while improving downside protection by 12% compared with benchmarks. The key contributions are the unification of ML forecasting and economic risk measures, demonstrable gains in both accuracy and resilience, and practical guidance for stakeholders in renewable-intensive markets.