arXiv:2607. 24256v1 Announce Type: cross Abstract: As communication networks adopt virtualized and disaggregated architectures, achieving energy efficiency has become increasingly important for both economic and environmental reasons.
arXiv:2608. 03589v1 Announce Type: new Abstract: We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs).
The paper presents an empirical benchmark of nine modern deep‑learning models for time‑series forecasting of smart‑meter energy consumption, evaluated on two publicly available datasets. It examines how historical input length, prediction horizon, and model architecture affect accuracy, finding that longer historical context improves performance up to a saturation point and that accuracy declines with longer horizons. The study also compares computational complexity, showing that lightweight architectures achieve similar performance to heavier models, and notes that model choice has limited impact across most demographic and household subgroups.
FeatureFormer is a neural performance predictor that adds explicit node-wise encodings of FLOPs, parameter counts, and memory proxies to a gated graph attention architecture. It is designed to improve latency and energy prediction for neural networks on edge devices, addressing the limitation of existing GNN and transformer predictors that largely ignore node-level computational cost. The authors also introduce NNEQ, a large-scale energy consumption dataset, and show through extensive experiments that FeatureFormer achieves state‑of‑the‑art performance across both metrics, including challenging out‑of‑domain settings, while the encoding can broadly enhance existing predictors with negligible overhead.
arXiv:2608. 13863v1 Announce Type: new Abstract: Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources.
The paper presents an empirical benchmark of nine deep learning models for smart meter energy forecasting, evaluating them on two public datasets. It examines how historical input length, prediction horizon, and model architecture affect accuracy, finding that longer historical context improves performance up to a saturation point while accuracy declines with longer horizons. The study also compares computational cost, showing lightweight models achieve similar accuracy to heavier ones, and notes that model choice matters less across most population segments.
arXiv:2606. 12742v1 Announce Type: new Abstract: Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector.
arXiv:2606. 23001v1 Announce Type: cross Abstract: On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck.
The paper benchmarks a range of AI methods—conventional ML, ensemble learning, deep neural networks, recurrent architectures, Transformers, graph models, and hybrid ensemble deep learning—on three renewable energy datasets, including large‑scale wave energy converter (WEC) data and wind farm SCADA measurements. Tree ensembles, particularly Extra Trees, outperform traditional ML and neural predictors on structured WEC layout data, achieving a 63.7% MAE reduction over an MLP baseline. Spatial‑temporal graph networks (STGCN) and an RF‑BiLSTM hybrid further improve forecasting accuracy, with the hybrid model reaching an MAE of 150.5 kW, a 75% reduction over a standalone LSTM and 10% better than STGCN. The study concludes that no single architecture dominates; randomized ensembles excel for structured surrogate modeling, graph networks for explicit spatial interactions, and hybrid recurrent ensembles for combined nonlinear tabular and temporal dynamics.
arXiv:2606. 27841v1 Announce Type: cross Abstract: The widespread adoption of Artificial Intelligence (AI) has led to increasing concerns about energy consumption, yet there is a lack of standardized methodologies to accurately estimate AI inference energy consumption, particularly across various tasks and architectures.
arXiv:2608. 11446v1 Announce Type: new Abstract: This paper presents a comparative study of two distinct approaches, XGBoost and Long-Short Term Memory (LSTM), for forecasting transmitted heat energy in District Heating Systems (DHS).
The paper benchmarks a range of AI methods—conventional ML, ensemble learning, deep neural networks, recurrent architectures, Transformers, graph models, and hybrid ensemble deep learning—on renewable energy datasets. Tree ensembles, especially Extra Trees, outperform other models on structured wave energy converter (WEC) layout data, reducing MAE by about 63.7% relative to an MLP baseline. The RF BiLSTM hybrid delivers the best overall forecasting accuracy for wind farm SCADA data, cutting MAE by roughly 75% compared to a standalone LSTM and surpassing STGCN by about 10%.
This paper presents a comparative study of two distinct approaches, XGBoost and Long-Short Term Memory (LSTM), for forecasting transmitted heat energy in District Heating Systems (DHS). The objective is to explore scenarios in which conventional ML algorithms demonstrate better performance over deep learning networks in time series forecasting and the associated benefits in terms of computational cost and environmental impact.