arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.16929eess.SPcs.AI
收藏

利用真实数据建模5G能耗:能量指纹是你所需的一切

Modelling the 5G Energy Consumption using Real-world Data: Energy Fingerprint is All You Need

Shenzhen Research Institute of Big Data(深圳大数据研究院);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院);School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳)科学与工程学院);Huawei Technologies(华为技术有限公司);School of Software Engineering, Tongji University(同济大学软件工程学院)

Tingwei Chen, Yantao Wang, Hanzhi Chen, Zijian Zhao, Xinhao Li, Nicola Piovesan, Guangxu Zhu, Qingjiang Shi

AI总结:

本文提出基于真实数据集的深度学习模型,通过整合基站标识符和引入掩码训练与注意力机制,有效提升了5G基站能耗估计的准确性。

摘要:

5G技术的引入革新了通信,实现了前所未有的容量、连接性和超快可靠的通信。然而,这一飞跃导致能耗显著增加,对网络可持续性构成了重大挑战。准确的能耗建模对于开发节能策略至关重要,使运营商能够在维持网络性能的同时优化资源利用。为此,我们提出了一种基于真实数据集的新型深度学习模型,用于5G基站能耗估计。与现有方法不同,我们的方法通过嵌入层将基站标识符(BSID)作为输入特征,捕捉不同基站之间的独特能耗模式。我们进一步引入了掩码训练方法和注意力机制以增强泛化能力和准确性。实验结果表明,我们的方法显著提高了性能,将平均绝对百分比误差(MAPE)从12.75%降低到4.98%,相比现有模型性能提升超过60%。我们的模型源代码可在https://github.com/RS2002/ARL获取。

英文摘要:

The introduction of 5G technology has revolutionized communications, enabling unprecedented capacity, connectivity, and ultra-fast, reliable communications. However, this leap has led to a substantial increase in energy consumption, presenting a critical challenge for network sustainability. Accurate energy consumption modeling is essential for developing energy-efficient strategies, enabling operators to optimize resource utilization while maintaining network performance. To address this, we propose a novel deep learning model for 5G base station energy consumption estimation based on a real-world dataset. Unlike existing methods, our approach integrates the Base Station Identifier (BSID) as an input feature through an embedding layer, capturing unique energy patterns across different base stations. We further introduce a masked training method and an attention mechanism to enhance generalization and accuracy. Experimental results show significant improvements, reducing Mean Absolute Percentage Error (MAPE) from 12.75% to 4.98%, achieving over 60% performance gain compared to existing models. The source code for our model is available at https://github.com/RS2002/ARL.

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。

↑