A Hybrid Autoencoder-Transformer Model for Robust Day-Ahead Electricity Price Forecasting under Extreme Conditions

📅 2025-04-25
🏛️ 2025 IEEE International Symposium on the Application of Artificial Intelligence in Electrical Engineering (AAIEE)
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
To address the low accuracy and poor robustness of day-ahead electricity price forecasting (DAEPF) under extreme weather and market anomalies, this paper proposes a Distillation-Attention Transformer with Autoencoder-based Self-Regression (DAT-ASR) framework. The method innovatively integrates a dynamic attention weight allocation mechanism and an unsupervised anomaly pattern separation module to jointly capture long- and short-term price dependencies while explicitly modeling anomalous disturbances. Furthermore, self-supervised pretraining enhances generalization in low-data anomaly scenarios. Experiments on California ISO and Shandong Power Market datasets demonstrate that DAT-ASR achieves 12.7%–18.3% lower average MAE than state-of-the-art models, reduces prediction errors during anomalous periods by over 25%, and improves inference speed by approximately 40%. These results substantiate significant gains in DAEPF accuracy, robustness, and practicality under extreme conditions.

Technology Category

Application Category

📝 Abstract
Accurate day-ahead electricity price forecasting (DAEPF) is critical for the efficient operation of power systems. Extreme weather condition and market anomalies pose significant challenges to existing forecasting methods. To this end, this paper proposes a novel hybrid deep learning framework that integrates a Distilled Attention Transformer (DAT) model and an Autoencoder Self-regression (ASR) model. The DAT leverages a self-attention mechanism to dynamically assign higher weights to critical segments of historical data, effectively capturing both long-term trends and short-term fluctuations. Concurrently, the ASR employs unsupervised learning to detect and isolate anomalous patterns induced by extreme conditions, such as heavy rain, heat waves, or human festivals. Experiments on datasets sampled from California and Shandong Province demonstrate that our framework significantly outperforms state-of-the-art methods in prediction accuracy, robustness, and computational efficiency. Our framework thus holds promise for enhancing grid resilience and optimizing market operations in future power systems.
Problem

Research questions and friction points this paper is trying to address.

Forecasting electricity prices accurately under extreme conditions and anomalies
Integrating transformer and autoencoder models to improve prediction robustness
Enhancing grid resilience and market operations in power systems
Innovation

Methods, ideas, or system contributions that make the work stand out.

Hybrid autoencoder-transformer model for electricity price forecasting
Distilled Attention Transformer captures long-term and short-term trends
Autoencoder Self-regression Model detects and isolates anomalous patterns
B
Boyan Tang
Beijing Normal-Hong Kong Baptist University, Zhuhai, Guangdong, China
X
Xuanhao Ren
Beijing Normal-Hong Kong Baptist University, Zhuhai, Guangdong, China
P
Peng Xiao
Beijing Normal-Hong Kong Baptist University, Zhuhai, Guangdong, China
S
Shunbo Lei
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China
X
Xiaorong Sun
School of Electrical and Power Engineering, Hohai University, Nanjing, Jiangsu, China
J
Jianghua Wu
Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Guangdong, China