Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
复制标题
DOI：
10.1109/tmlcn.2024.3352569
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Flor Ortíz;N. Skatchkovsky;E. Lagunas;W. Martins;G. Eappen;Saed Daoud;Osvaldo Simeone;Bipin Rajendran;S. Chatzinotas
中科院分区：
文献类型：
--
作者：
Flor Ortíz;N. Skatchkovsky;E. Lagunas;W. Martins;G. Eappen;Saed Daoud;Osvaldo Simeone;Bipin Rajendran;S. Chatzinotas
最新的卫星通信(SatCom)任务的特点是完全可重新配置的星载软件定义的有效载荷，能够使无线电资源适应系统流量的时间和空间变化。由于纯粹基于优化的解决方案计算繁琐且缺乏灵活性，基于机器学习(ML)的方法已成为有前途的替代方法。我们研究了能量高效的大脑启发的ML模型在星载无线资源管理中的应用。除了软件模拟，我们还报告了利用最近发布的Intel Loihi 2芯片的广泛实验结果。为了测试模型的性能，我们在Xilinx Versal VCK5000上实现了传统的卷积神经网络(CNN)，并对不同交通需求的准确率、精确度、召回率和能量效率进行了详细的比较。最值得注意的是，与基于CNN的参考平台相比，在Loihi 2上实施的尖峰神经网络(SNN)可以产生更高的精确度，同时将功耗降低100倍以上。我们的发现指出了神经形态计算和SNN在支持星载卫星通信操作方面的巨大潜力，为提高未来卫星通信系统的效率和可持续性铺平了道路。
The latest Satellite Communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally tedious and to lack flexibility, Machine Learning (ML)-based methods have emerged as promising alternatives. We investigate the application of energy-efficient brain-inspired ML models for on-board radio resource management. Apart from software simulation, we report extensive experimental results leveraging the recently released Intel Loihi 2 chip. To benchmark the performance of the proposed model, we implement conventional Convolutional Neural Networks (CNN) on a Xilinx Versal VCK5000, and provide a detailed comparison of accuracy, precision, recall, and energy efficiency for different traffic demands. Most notably, for relevant workloads, Spiking Neural Networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than $100\times $ as compared to the CNN-based reference platform. Our findings point to the significant potential of neuromorphic computing and SNNs in supporting on-board SatCom operations, paving the way for enhanced efficiency and sustainability in future SatCom systems.