AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms
AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms
复制标题
DOI：
10.1109/bigdata55660.2022.10021101
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Mohamed Elmahallawy;Tie Luo
中科院分区：
文献类型：
--
作者：
Mohamed Elmahallawy;Tie Luo
低地球轨道（LEO）星座，每个星座都包括大量的卫星，已经成为“来自天空”的大数据的新来源。将这些数据下载到地面站（GS）进行大数据分析需要非常高的带宽，并且涉及很大的传播延迟。联邦学习（FL）提供了一个很有前途的解决方案，因为它允许数据保持原位（永远不会离开卫星），并且只需要传输机器学习模型参数（在卫星数据上训练）。然而，传统的同步FL过程可能需要几天的时间来训练一个单一的FL模型的背景下，卫星通信（Satcom），由于一个瓶颈所造成的掉队卫星。在本文中，我们提出了一个异步FL框架的LEO星座称为AsyncFLEO，以提高FL效率的卫星通信。AsynFLEO不仅解决了同步FL中的瓶颈（空闲等待），而且还解决了由离散卫星引起的模型失效问题。AsyncFLEO利用定位在“天空中”的高空平台（HAP）作为参数服务器，并且由三个技术组件组成：（1）星环通信拓扑，（2）模型传播算法，以及（3）具有卫星分组和陈旧折扣的模型聚合算法。我们对IID和非IID数据的广泛评估表明，AsyncFLEO的性能大大优于现有技术，收敛延迟减少了22倍，准确度提高了40%。
Low Earth Orbit (LEO) constellations, each comprising a large number of satellites, have become a new source of big data "from the sky". Downloading such data to a ground station (GS) for big data analytics demands very high bandwidth and involves large propagation delays. Federated Learning (FL) offers a promising solution because it allows data to stay in-situ (never leaving satellites) and it only needs to transmit machine learning model parameters (trained on the satellites’ data). However, the conventional, synchronous FL process can take several days to train a single FL model in the context of satellite communication (Satcom), due to a bottleneck caused by straggler satellites. In this paper, we propose an asynchronous FL framework for LEO constellations called AsyncFLEO to improve FL efficiency in Satcom. Not only does AsynFLEO address the bottleneck (idle waiting) in synchronous FL, but it also solves the issue of model staleness caused by straggler satellites. AsyncFLEO utilizes high altitude platforms (HAPs) positioned "in the sky" as parameter servers, and consists of three technical components: (1) a ring-of-stars communication topology, (2) a model propagation algorithm, and (3) a model aggregation algorithm with satellite grouping and staleness discounting. Our extensive evaluation with both IID and non-IID data shows that AsyncFLEO outperforms the state of the art by a large margin, cutting down convergence delay by 22 times and increasing accuracy by 40%.