arXiv 2512.150672026-06-24cs.LGcs.AIcs.SYeess.SY

EMFusion: 一种考虑不确定性的条件扩散框架用于无线网络中频率选择性电磁场预测

EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting

department of Electrical Engineering and Computer Science, York University（电气工程与计算机科学系，约克大学）；School of Electrical and Electronic Engineering, Huazhong University of Science and Technology（电子与电气工程学院，华中科技大学）；Central China Branch of State Grid Corporation of China（国家电网公司中部分部）；Department of Electronic Engineering, University of Rome Tor Vergata（罗马大学Tor Vergata电子工程系）；Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT)（国家大学间电信研究会（CNIT））

Zijiang Yan, Yixiang Huang, Jianhua Pei, Hina Tabassum, Luca Chiaraviglio

备注：: Accepted in IEEE Transactions on Network Science and Engineering

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出EMFusion框架，通过整合时间、季节等上下文因素，提供不确定性估计，以提升无线网络中频率选择性电磁场预测的准确性。

摘要：

无线基础设施的快速增长增加了准确估计和预测电磁场（EMF）水平的必要性，以确保持续合规、评估潜在健康影响并支持高效网络规划。尽管现有研究依赖于宽频带聚合EMF数据的单变量预测，但需要频率选择性多变量预测来捕捉跨运营商和频率的变化，以支持前瞻性网络规划。为此，本文介绍了EMFusion，一种基于条件多变量扩散的概率预测框架，整合了多种上下文因素，如时间、季节和节假日，同时提供明确的不确定性估计。所提出的架构特征是增强的残差U-Net主干，结合交叉注意力机制，动态整合外部条件以指导生成过程。此外，EMFusion集成了基于填补的采样策略，将预测视为结构补全任务，确保时间一致性，即使有不规则测量。与标准点预测器不同，EMFusion从学习的条件分布中生成经验概率预测区间，提供不确定性意识的概率预测，而不是简单的点估计。在频率选择性EMF数据集上进行的数值实验表明，EMFusion在工作时间的上下文信息下优于基线模型，无论是有还是没有条件。EMFusion在连续排名概率分数（CRPS）上比最佳基线高出23.85%，在归一化均方根误差上高出13.93%，并将预测CRPS误差减少了22.47%。

英文摘要：

The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, multivariate narrow-band EMF forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper introduces EMFusion, a conditional diffusion-based EMF forecasting framework that integrates diverse contextual factors, such as time of day, season, and holidays, while providing uncertainty-aware probabilistic forecasts. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. Unlike standard point forecasters, EMFusion generates empirical probabilistic prediction intervals from the learned conditional distribution, providing uncertainty-aware probabilistic forecasting rather than simple point estimation. Numerical experiments conducted on the multivariate narrow-band EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. The proposed EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS) and 13.93% in normalized root mean square error.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。