Agent improves wind power forecasts by adjusting to changing weather
Guarded Agent-in-the-Loop Residual Adaptation for Evolving Wind Power Regimes
Multiagent Systems
Summary
Wind power predictions can be less accurate during unusual weather events like storms or heatwaves. The authors created a system that keeps the main forecast model the same but adds small corrections based on current weather conditions. An agent watches recent errors and decides when to apply these corrections, helping forecasts become more accurate over time. This approach was tested with multiple forecast models and consistently reduced prediction errors at different future times.
What this means in practice
- •For renewable energy operators: Improve accuracy of wind power forecasts during changing weather patterns for better grid management.
- •For energy forecasting software teams: Integrate adaptive residual experts that adjust predictions based on detected weather regimes and recent errors in wind power models.
Authors
Yuhang Dong, Min Xia, Jinghong Li, Yue Dai, Xinyue Wang, Shi Liang
Abstract
Wind power forecasting models are often deployed as fixed temporal backbones, but the errors they make can vary across meteorological regimes such as cold waves, heat-and-calm periods, productive typhoon, and destructive storms. We present a guarded Agent-in-the-loop residual adaptation framework that leaves the temporal backbone unchanged and adapts only a small set of scene-conditioned residual experts. An Agent layer interprets external scene information, identifies the current regime, selects residual experts, and applies a correction only when recent observed errors support it. New experts enter the pool after they outperform their initializations on a validation set, keeping model growth under explicit control. Backbone-only and Agent-enhanced forecasts are compared at lead times of 4, 8, 12, 24, and 48 across nine time-series backbones. Across these runs, the guarded framework lowers both MAE and RMSE for all 45 backbone-horizon combinations, with average MAE reductions ranging from 11.21% to 20.26% across backbones. Online-selection baselines, component ablations, and routing analyses identify the roles of residual experts, scene-aware routing, and the online acceptance rule. Candidate-scene runs evaluate the promotion path under controlled conditions; long-term unattended deployment was not evaluated.