.png){kind=icon}
.png){kind=icon}
Return
BLIP: A BiGRU-Based Framework for Load Decomposition and Electricity Consumption Behavior Pattern Recognition in Smart Grids
.png){kind=icon}
PRE
AI
F
H
Q
X
DOI：10.1142/S0218001426500060.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate load decomposition and behavior pattern recognition are critical for efficient energy management and personalized demand response in modern smart grids. However, existing methods often struggle to capture complex temporal dependencies in electricity consumption data and rely heavily on manual feature engineering, limiting their accuracy and adaptability. To address these challenges, this paper proposes BLIP, a novel BiGRU-based framework for load decomposition and electricity consumption behavior pattern recognition. By leveraging the bidirectional temporal modeling capability of BiGRU networks, BLIP accurately decomposes aggregated load signals into distinct components, capturing both past and future dependencies. The framework further exploits the decomposed load features to recognize personalized electricity consumption patterns, enabling fine-grained differentiation of user or device behaviors. Unlike traditional approaches, BLIP performs end-to-end learning, improving robustness and generalization in complex power system environments. BLIP incorporates a unique adaptation to the BiGRU architecture, enabling better handling of irregular load fluctuations and introducing a novel attention mechanism for enhanced behavior pattern recognition. This adaptation is particularly effective in addressing challenges like inaccurate peak load forecasting and excessive energy consumption, which are common in smart grid systems. Experimental results on real-world datasets demonstrate that BLIP significantly enhances both load disaggregation accuracy and behavioral pattern identification, supporting more intelligent and efficient energy management.
Keywords:
Load decomposition
electricity consumption behavior
deep learning
pattern recognition
Journal
IF:
1.1
Papers:
161
Citations:
2.0K
Organization
Cited Papers