A Methodology to Assess Power Modeling in Energy-Aware Federated Learning on Heterogeneous Mobile Devices

• URL: http://arxiv.org/abs/2605.27601v1
• Date: Tue, 26 May 2026 19:19:31 GMT
• Title: A Methodology to Assess Power Modeling in Energy-Aware Federated Learning on Heterogeneous Mobile Devices
• Abstract summary: Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains.<n>We propose a reproducible CPU power estimation methodology combined with a rail-to-cluster mapping technique to retrieve cluster-level supply voltage.<n>We show that the analytical model predicts CPU power with errors below 10%, whereas the approximate model incurs errors of up to 959%.
• Score: 0.34410212782758043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains. As a result, state-of-the-art energy-aware Federated Learning (FL) frameworks typically rely on simplified approximate power models to estimate computation energy, rather than the more accurate analytical CMOS-based model. To bridge this gap, we propose a reproducible CPU power estimation methodology combined with a rail-to-cluster mapping technique to retrieve cluster-level supply voltage. We evaluate our approach on two commodity Android devices and show that the analytical model predicts CPU power with errors below 10%, whereas the approximate model incurs errors of up to 959%. Using AnycostFL, a state-of-the-art energy-aware FL framework, we show that the analytical model achieves the same 80% model accuracy while consuming 1.4x less energy than the approximate model. These results highlight that approximate models can severely misestimate computation energy and lead to suboptimal decisions. This work facilitates the use of analytical CPU power models on heterogeneous multi-cluster ARM-based mobile SoCs without additional hardware support or external power measurement tools.

Related papers

• A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration [1.2419540081875826]
  This paper explores the theoretical underpinnings of various AI model optimization techniques, algorithms, and abstractions.<n>We propose a comprehensive hardware (HW) and model-agnostic generalized optimization architecture that integrates these techniques for improved efficiency.<n>As a concrete demonstration, we show that GOE-compressed language models deploy and run on a GPU-less edge CPU, and that the choice of compression method, not merely its nominal bit-width, determines whether task accuracy survives deployment.
  arXiv  Detail & Related papers  (2026-08-19T23:30:16Z)
• A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers [7.256390775982009]
  We propose the first physics-informed time-series model that can accurately forecast power utilization of an AI data center 5-80 minutes into the future.<n>The model is trained and evaluated on a real AI data center dataset and is more accurate than the state-of-the-art (SOTA) models tested.<n>Relative to the SOTA transformer-based and non-transformer-based models, improvements in forecasting accuracy range from 0.782%-39.08% for MSE, 0.993%-51.82% for MAE, and 0.370%-22.28% for RMSE.
  arXiv  Detail & Related papers  (2026-04-14T04:14:32Z)
• GPU-accelerated simulated annealing based on p-bits with real-world device-variability modeling [1.2375561840897742]
  Probabilistic computing using p-bits (p-bits) is an efficient alternative to CMOS logic for complex problem-solving.<n>This paper introduces a GPU-accelerated, open-source simulated framework based on p-bits.<n>By providing a scalable and accessible tool, this framework aims to advance research in probabilistic computing.
  arXiv  Detail & Related papers  (2026-01-20T20:59:21Z)
• Energy Scaling Laws for Diffusion Models: Quantifying Compute and Carbon Emissions in Image Generation [50.21021246855702]
  We propose an adaptation of Kaplan scaling laws to predict GPU energy consumption for diffusion models based on computational complexity (FLOPs)<n>Our approach decomposes diffusion model inference into text encoding, iterative denoising, and decoding components, with the hypothesis that denoising operations dominate energy consumption due to their repeated execution across multiple inference steps.<n>Our results validate the compute-bound nature of diffusion inference and provide a foundation for sustainable AI deployment planning and carbon footprint estimation.
  arXiv  Detail & Related papers  (2025-11-21T08:12:47Z)
• Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge [3.1471494780647795]
  Recent trends show a growing focus on compact models-typically under 10 billion parameters-enabled by techniques such as quantization.<n>This shift paves the way for LMs on edge devices, offering potential benefits such as enhanced privacy, reduced latency, and improved data sovereignty.<n>We present a comprehensive evaluation of generative LM inference on representative CPU-based and GPU-accelerated edge devices.
  arXiv  Detail & Related papers  (2025-03-12T07:01:34Z)
• Decentralized Diffusion Models [53.89995588977048]
  Large-scale AI model training divides work across thousands of GPU, then synchronizes gradients across them at each step.<n>This incurs a significant network burden that only centralized, monolithic clusters can support.<n>We propose Decentralized Diffusion Models, a scalable framework for distributing diffusion model training across independent clusters.
  arXiv  Detail & Related papers  (2025-01-09T18:59:56Z)
• Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One [83.5162421521224]
  We propose a unique method termed E-ARM for training autoregressive generative models. E-ARM takes advantage of a well-designed energy-based learning objective. We show that E-ARM can be trained efficiently and is capable of alleviating the exposure bias problem.
  arXiv  Detail & Related papers  (2022-06-26T10:58:41Z)
• Physics-informed linear regression is a competitive approach compared to Machine Learning methods in building MPC [0.8135412538980287]
  We show that control in general leads to satisfactory reductions in heating and cooling energy compared to the building's baseline controller. We also see that the physics-informed ARMAX models have a lower computational burden, and a superior sample efficiency compared to the Machine Learning based models.
  arXiv  Detail & Related papers  (2021-10-29T16:56:05Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Power Modeling for Effective Datacenter Planning and Compute Management [53.41102502425513]
  We discuss two classes of statistical power models designed and validated to be accurate, simple, interpretable and applicable to all hardware configurations and workloads. We demonstrate that the proposed statistical modeling techniques, while simple and scalable, predict power with less than 5% Mean Absolute Percent Error (MAPE) for more than 95% diverse Power Distribution Units (more than 2000) using only 4 features.
  arXiv  Detail & Related papers  (2021-03-22T21:22:51Z)
• Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration [130.89746032163106]
  We propose ALOE, a new algorithm for learning conditional and unconditional EBMs for discrete structured data. We show that the energy function and sampler can be trained efficiently via a new variational form of power iteration. We present an energy model guided fuzzer for software testing that achieves comparable performance to well engineered fuzzing engines like libfuzzer.
  arXiv  Detail & Related papers  (2020-11-10T19:31:29Z)
• An Ensemble Learning Approach for In-situ Monitoring of FPGA Dynamic Power [20.487660974785943]
  We present and evaluate a power monitoring scheme capable of accurately estimating the runtime dynamic power of FPGAs. We describe a novel and specialized ensemble model which can be decomposed into multiple customized base learners. In experiments, we first show that a single decision tree model can achieve prediction error within 4.51% of a commercial gate-level power estimation tool.
  arXiv  Detail & Related papers  (2020-09-03T03:39:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.