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