Scholarlink

<p>Weather risk in high-solar power systems affects generation, prices, and imbalance exposure. Public forecasting pipelines use numerical weather prediction and operator forecasts, but forecast-discussion judgment remains difficult to structure. We evaluate a constrained language-model extraction design that converts NWS Area Forecast Discussions into bounded weather-risk features. The CAISO-SP15 public-data test bed combines system-level solar generation, day-ahead and real-time price proxies, HRRR forecasts, and NWS discussions. Photovoltaic and price forecasts are propagated through 100-scenario day-block residual-bootstrap scenarios into a CVaR-regularized settlement-proxy quantity rule. In 2024–2025 full-HRRR neural forecasts, the LLM cloud-rule path produced descriptive mean all-hour PV RMSE of 1167.35 MW, compared with 1186.03 MW for no text and 1221.09 MW for keyword rules; time-based support differs by metric and comparison. For real-time prices, LLM-rule weather scores produced descriptive mean RMSE of 17.94 USD/MWh, compared with 18.47 USD/MWh for rule-text scores. In ex-post public-data proxy accounting with a common rule-core anchor and matched <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(w=0.50\)</EquationSource></InlineEquation> blend, the LLM scenario path increased proxy value by 45.24 million USD, reduced <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(\textrm{CVaR}_{95}\)</EquationSource></InlineEquation> loss by 5.84 thousand USD per hour, and reduced imbalance by 852.7 GWh. These results support public weather narratives as an auditable residual-information layer for solar forecasting and settlement-proxy risk evaluation.</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

From public weather narratives to solar-market risk decisions using constrained language-model features

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月13日

查看全文
  • Yuqi Zhou,
  • Xiangrui Meng,
  • Jing Qiu,
  • Junhua Zhao

摘要

Weather risk in high-solar power systems affects generation, prices, and imbalance exposure. Public forecasting pipelines use numerical weather prediction and operator forecasts, but forecast-discussion judgment remains difficult to structure. We evaluate a constrained language-model extraction design that converts NWS Area Forecast Discussions into bounded weather-risk features. The CAISO-SP15 public-data test bed combines system-level solar generation, day-ahead and real-time price proxies, HRRR forecasts, and NWS discussions. Photovoltaic and price forecasts are propagated through 100-scenario day-block residual-bootstrap scenarios into a CVaR-regularized settlement-proxy quantity rule. In 2024–2025 full-HRRR neural forecasts, the LLM cloud-rule path produced descriptive mean all-hour PV RMSE of 1167.35 MW, compared with 1186.03 MW for no text and 1221.09 MW for keyword rules; time-based support differs by metric and comparison. For real-time prices, LLM-rule weather scores produced descriptive mean RMSE of 17.94 USD/MWh, compared with 18.47 USD/MWh for rule-text scores. In ex-post public-data proxy accounting with a common rule-core anchor and matched \(w=0.50\) blend, the LLM scenario path increased proxy value by 45.24 million USD, reduced \(\textrm{CVaR}_{95}\) loss by 5.84 thousand USD per hour, and reduced imbalance by 852.7 GWh. These results support public weather narratives as an auditable residual-information layer for solar forecasting and settlement-proxy risk evaluation.