Orbital Edge Computing

Abstract

Advances in nanosatellite technology and a declining cost of access to space have fostered an emergence of large constellations of sensor-equipped satellites in low-Earth orbit. Many of these satellite systems operate under a "bent-pipe" architecture, in which ground stations send commands to orbit and satellites reply with raw data. In this work, we observe that a bent-pipe architecture for Earth-observing satellites breaks down as constellation population increases. Communication is limited by the physical configuration and constraints of the system over time, such as ground station location, nanosatellite antenna size, and energy harvested on orbit. We show quantitatively that nanosatellite constellation capabilities are determined by physical system constraints.We propose an Orbital Edge Computing (OEC) architecture to address the limitations of a bent-pipe architecture. OEC supports edge computing at each camera-equipped nanosatellite so that sensed data may be processed locally when downlinking is not possible. In order to address edge processing latencies, OEC systems organize satellite constellations into computational pipelines. These pipelines parallelize both data collection and data processing based on geographic location and without the need for cross-link coordination. OEC satellites explicitly model constraints of the physical environment via a runtime service. This service uses orbit parameters, physical models, and ground station positions to trigger data collection, predict energy availability, and prepare for communication. We show that an OEC architecture can reduce ground infrastructure over 24× compared to a bent-pipe architecture, and we show that pipelines can reduce system edge processing latency over 617×.Computational nanosatellite architects face three key challenges. First, physical constraints on nanosatellite design (e.g.

Beijing Language and Culture University, China

“…The wide availability of satellite services has resulted in a significant surge in the amount of data stored onboard. The amount of data generated by remote sensing satellites worldwide far exceeds the capacity for timely downloading at present [2]. Even with the use of a higher frequency Ku/Ka band for downloading, it is impossible to complete the download of all data within a single satellite transit window.…”

“…Bhattacherjee et al [10] initiated a scholarly discourse on the concept of satellite edge computing, exploring potential applications that could leverage this paradigm as well as identifying factors that could hinder its implementation. Denby et al [11] proposed using the nanosatellite orbital edge computing to tackle limitations of the "bent-pipe" architecture. Driven by remote sensing services, the authors presented a working mode of computational nanosatellite pipeline to eliminate the problem of single satellite energy constraints.…”

A Survey on Technologies, Standards and Open Challenges in Satellite IoT

“…From satellite perspective, there are two options of integrating edge computing in this pipeline: at the IoT nodes, or in orbit, at the satellite. For example, satellite constellations be thought operating as computational pipelines: studies in [103] for camera equipped satellites sensing the Earth show advantages both in terms of architecture infrastructure and in processing latency for this approach. But the edge computing paradigm does not only shift processing nearer to the location where the data is generated and/or consumed, but also introduce the application virtualization paradigm in, thus pushing the technology towards more standardized approaches.…”

Edge Selection and Clustering for Federated Learning in Optical Inter-LEO Satellite Constellation

“…Benefited from low-cost deployment, dense LEOs forming mega-constellations are empowered with on-board computation capability [10], [11]. LEOs will be capable of providing more complex and globally-covered services, or even collaborative training tasks.…”