Work

A Contextually Enhanced Self-Attention Dilated RNN for Load Forecasting

Year: 2025

Type: conference-paper

Abstract: Accurate load forecasting is critical for optimizing energy systems, as prediction accuracy directly impacts efficiency and reliability, particularly in complex temporal dynamics. This paper proposes a novel model integrating contextual enhanced positional encoding (CoPE) with self-attention to address long forecasting horizons and intricate temporal dependencies. By incorporating dilated sparse skip connections into the recurrent neural network (RNN) architecture, the model enhances computational efficiency in long-sequence processing, while self-attention mechanism captures global dependencies across time steps. Additionally, local convolution-based positional encoding strengthens the model’s ability to capture periodic patterns and trend variations in power loads. Experimental results demonstrate that the proposed approach achieves high predictive accuracy and robust stability in short-term load forecasting.

Source: IEEE Smart World Congress (SWC)

DOI: 10.1109/swc65939.2025.00110

Authors: Heng Li, Hanzhao Lv, Qi Liu, Xiaodong Liu, Yonghong Zhang, Xiaokang Zhou

Institutions: Nanjing University of Information Science and Technology, Edinburgh Napier University, Kansai University

Language: English

Topic: Energy Load and Power Forecasting

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: green

Funder: National Natural Science Foundation of China