LAD-BNet: Lag-Aware Dual-Branch Networks for Real-Time Energy Forecasting on Edge Devices

arXiv — stat.MLTuesday, December 9, 2025 at 5:00:00 AM
  • LAD-BNet, a Lag-Aware Dual-Branch Network, has been introduced as a novel neural architecture aimed at enhancing real-time energy forecasting on edge devices, specifically optimized for Google Coral TPU. This model effectively combines temporal lag exploitation with a Temporal Convolutional Network (TCN) to capture both short and long-term dependencies, achieving a mean absolute percentage error (MAPE) of 14.49% at a one-hour forecasting horizon.
  • The development of LAD-BNet is significant as it represents a substantial improvement in energy forecasting capabilities, achieving an inference time of just 18ms on Edge TPU, which is 8-12 times faster than traditional CPU methods. This advancement is crucial for optimizing smart grid operations and enhancing the efficiency of intelligent buildings.
  • The introduction of LAD-BNet aligns with ongoing trends in deep learning, where hybrid models combining various architectures, such as LSTM and TCN, are increasingly utilized for complex forecasting tasks. This reflects a broader shift towards leveraging advanced neural networks to improve predictive accuracy across various domains, including energy management and market behavior prediction.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling
PositiveArtificial Intelligence
The introduction of RewriteNets marks a significant advancement in generative sequence modeling, utilizing a novel architecture that employs explicit, parallel string rewriting instead of the traditional dense attention weights found in models like the Transformer. This method allows for more efficient processing by performing fuzzy matching, conflict resolution, and token propagation in a structured manner.
Hybrid SARIMA LSTM Model for Local Weather Forecasting: A Residual Learning Approach for Data Driven Meteorological Prediction
NeutralArtificial Intelligence
A new study presents a Hybrid SARIMA LSTM model aimed at improving local weather forecasting through a residual learning approach, addressing the challenges posed by the chaotic nature of atmospheric systems. Traditional models like SARIMA struggle with sudden, nonlinear transitions in temperature data, leading to systematic errors in predictions. The hybrid model seeks to enhance accuracy by integrating the strengths of both SARIMA and LSTM methodologies.

Ready to build your own newsroom?

Subscribe to unlock a personalised feed, podcasts, newsletters, and notifications tailored to the topics you actually care about