The Informer model leverages its innovative ProbSparse self-attention mechanism to demonstrate significant performance advantages in long-sequence time-series forecasting tasks. However, when confronted with time-series data exhibiting multi-scale characteristics and substantial noise, the model’s attention mechanism reveals inherent limitations. Specifically, the model is susceptible to interference from local noise or irrelevant patterns, leading to diminished focus on globally critical information and consequently impairing forecasting accuracy. To address this challenge, this study proposes an enhanced architecture that integrates a Gated Attention mechanism into the original Informer framework. This mechanism employs learnable gating functions to dynamically and selectively impose differentiated weighting on crucial temporal segments and discriminative feature dimensions within the input sequence. This adaptive weighting strategy is designed to effectively suppress noise interference while amplifying the capture of core dynamic patterns. Consequently, it substantially strengthens the model’s capability to represent complex temporal dynamics and ultimately elevates its predictive performance.