AI 中文总结
本文针对ERCOT日前市场，提出制度敏感型XAI框架，采用HGBR与抑制比量化价格滞后对物理参数的掩盖程度，发现价格尖峰源于特定温度范围的系统反应，为电价预测模型优化提供依据。
AI 中文摘要
准确的电价预测对智能电网稳定至关重要，但现代预测模型过度依赖历史价格滞后项，往往会掩盖市场波动的基本物理驱动因素。本文提出一种 regime-sensitive（制度敏感型）可解释人工智能（XAI）框架，以揭示负荷、气候和日历变量在2014-2024年ERCOT日前市场中的隐藏作用。采用基于直方图的梯度提升回归器（HGBR），我们引入抑制比来量化价格滞后项掩盖物理参数的程度。分析表明，尽管在正常情况下滞后项提供短期记忆，但它们无法捕捉极端动态；值得注意的是，加入滞后项会在价格尖峰期间增加预测误差（平均绝对误差MAE/均方根误差RMSE）。通过分离这些效应，研究发现价格尖峰并非仅仅是持续升温的结果，而是系统在特定温度范围内急剧反应的产物。这些发现强调了摆脱基于滞后项的模型以揭示极端价格事件真实驱动因素的重要性。
英文摘要
Accurate electricity price forecasting is critical for smart grid stability, yet the heavy reliance on historical price lags in modern predictive models often obscures the fundamental physical drivers of market volatility. This paper proposes a regime-sensitive, explainable artificial intelligence (XAI) framework to unmask the hidden roles of load, climate, and calendar variables in the ERCOT Day-Ahead Market (2014-2024). Utilizing a Histogram-based Gradient Boosting Regressor (HGBR), we introduce a Suppression Ratio to quantify how price lags overshadow physical parameters. Our analysis reveals that while lags provide short-term memory during normal conditions, they fail to capture extreme dynamics; notably, their inclusion increased forecasting error (MAE/RMSE) during price spikes. By isolating these effects, the study revealed that price spikes are not merely the result of continuously rising temperatures, but rather emerge from the system reacting sharply within a specific temperature range. These findings underscore the importance of moving beyond lag-based models to uncover the true drivers of extreme price events.
CommentsAccepted at IEEE SmartGridComm 2026
