Salvato in:
Dettagli Bibliografici
Autore principale: Lignier, Jean-Philippe
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.10680
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911305955278848
author Lignier, Jean-Philippe
author_facet Lignier, Jean-Philippe
contents Real-time energy forecasting on edge devices represents a major challenge for smart grid optimization and intelligent buildings. We present LAD-BNet (Lag-Aware Dual-Branch Network), an innovative neural architecture optimized for edge inference with Google Coral TPU. Our hybrid approach combines a branch dedicated to explicit exploitation of temporal lags with a Temporal Convolutional Network (TCN) featuring dilated convolutions, enabling simultaneous capture of short and long-term dependencies. Tested on real energy consumption data with 10-minute temporal resolution, LAD-BNet achieves 14.49% MAPE at 1-hour horizon with only 18ms inference time on Edge TPU, representing an 8-12 x acceleration compared to CPU. The multi-scale architecture enables predictions up to 12 hours with controlled performance degradation. Our model demonstrates a 2.39% improvement over LSTM baselines and 3.04% over pure TCN architectures, while maintaining a 180MB memory footprint suitable for embedded device constraints. These results pave the way for industrial applications in real-time energy optimization, demand management, and operational planning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10680
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LAD-BNet: Lag-Aware Dual-Branch Networks for Real-Time Energy Forecasting on Edge Devices
Lignier, Jean-Philippe
Machine Learning
Real-time energy forecasting on edge devices represents a major challenge for smart grid optimization and intelligent buildings. We present LAD-BNet (Lag-Aware Dual-Branch Network), an innovative neural architecture optimized for edge inference with Google Coral TPU. Our hybrid approach combines a branch dedicated to explicit exploitation of temporal lags with a Temporal Convolutional Network (TCN) featuring dilated convolutions, enabling simultaneous capture of short and long-term dependencies. Tested on real energy consumption data with 10-minute temporal resolution, LAD-BNet achieves 14.49% MAPE at 1-hour horizon with only 18ms inference time on Edge TPU, representing an 8-12 x acceleration compared to CPU. The multi-scale architecture enables predictions up to 12 hours with controlled performance degradation. Our model demonstrates a 2.39% improvement over LSTM baselines and 3.04% over pure TCN architectures, while maintaining a 180MB memory footprint suitable for embedded device constraints. These results pave the way for industrial applications in real-time energy optimization, demand management, and operational planning.
title LAD-BNet: Lag-Aware Dual-Branch Networks for Real-Time Energy Forecasting on Edge Devices
topic Machine Learning
url https://arxiv.org/abs/2511.10680