Abstract Accurate multi-horizon load forecasting is essential for the stability and efficiency of smart grid operations, particularly in residential environments where electricity consumption patterns are shaped by both long-term trends and short-term fluctuations. While Transformer-based models —such as Autoformer— have advanced forecasting accuracy by leveraging frequency-domain attention for capturing periodic behavior, they often struggle with rapidly changing, localized patterns prevalent in real-world data.To address this challenge, we propose CLM-Former, a novel hybrid deep learning architecture that integrates time series decomposition, an autocorrelation-based attention mechanism, and a tailored subnetwork, CLM-subNet, which combines convolutional and recurrent layers. This design enables the model to effectively capture both seasonal dependencies and high-resolution variations in electricity usage, thereby enhancing its performance across multiple forecasting horizons.Comprehensive evaluations on real-world smart meter data demonstrate the robustness and adaptability of CLM-Former against a range of Transformer-based and deep learning baselines. Its superior ability to model both long-term periodic structures and short-term dynamics establishes CLM-Former as a promising solution for residential energy forecasting, with potential implications for demand response, distributed scheduling, and future smart grid management strategies.
Rahmatinia et al. (Wed,) studied this question.