From science fiction to practice: China has begun construction of the world's first space computing center
- Gabriele Iuvinale
- 1 giorno fa
- Tempo di lettura: 4 min
China successfully launched a group of 12 satellites on Wednesday aboard a Long March-2D carrier rocket, marking the debut deployment of a space computing satellite constellation, dubbed the "Three-Body Computing Constellation".
The constellation is designed to perform real-time data processing in orbit, addressing efficiency issues in traditional satellite systems and accelerating the integration of artificial intelligence into space-based applications.
The project reflects China's growing ambitions to extend its computing power into space, an emerging frontier that could eventually complement terrestrial cloud infrastructure and support data-intensive applications like AI and remote sensing.
At 12:12 p.m. on Wednesday, May 14, China launched the Space Computing Satellite Constellation (SCSC) into orbit from the Jiuquan Satellite Launch Center (JSLCC) using the Long March 2-D carrier rocket. This is the world's first space computing satellite constellation, which will open a new chapter in the global era of “space computing.”
Jointly developed by Zhejiang Lab – a research institute based in Hangzhou, east China's Zhejiang Province – and international partners, the constellation is designed to eventually comprise thousands of satellites with a combined computing power of 1,000 peta operations per second (POPS), according to Wang Jian, a member of the Chinese Academy of Engineering and the director of the lab. Wang is also the founder of Alibaba Cloud – one of China's leading cloud computing platforms.
The constellation is designed to perform real-time data processing in orbit, addressing efficiency issues in traditional satellite systems and accelerating the integration of artificial intelligence into space-based applications.
Each satellite in this initial batch is equipped with a domestically developed 8-billion-parameter AI model capable of processing satellite data across levels L0 to L4 (with L0 referring to raw data directly collected by the satellite). The constellation also supports full inter-satellite connectivity.
In addition to AI-powered data processing, the satellites will carry out experimental missions, including cross-orbit laser communication and astronomical science observations.
What is it specifically about?
A space computing satellite constellation is a network of multiple satellites in orbit that are designed to work together to provide significant computing power in space.
Key aspects and objectives of such a constellation include:
In-orbit data processing: Unlike traditional satellite systems where raw data is downlinked to Earth for processing, a space computing constellation aims to perform data analysis and computation directly in space. This significantly reduces latency and bandwidth requirements for data transmission.
Enhanced AI capabilities in space: By providing substantial computing resources, these constellations can facilitate the deployment and execution of complex artificial intelligence (AI) algorithms for various space-based applications.
Real-time applications: The ability to process data in orbit enables real-time or near real-time applications such as Earth observation with immediate insights, faster disaster response, and autonomous spacecraft operations.
Scalability: A constellation approach allows for increased computing power and resilience by adding more satellites to the network.
According to available information, the 12 computing satellites of the first constellation of the “Star Computing” program adopt the networked intelligent satellite platform researched by Guoxing Aerospace and carry loads such as intelligent star computers and high-speed star routers from Zhijiang Laboratory, realizing the “computing power in the sky and network formation in orbit.”
Each satellite is equipped with a star-based intelligent computing system and an interstellar communication system and carries on board an interstellar intelligent computing system and an interstellar communication system, with space-based computing and space-based interconnection capabilities,.
With the high-speed interstellar laser interconnection, stable constellation network and distributed computing power scheduling, the constellation will build a space computing system, i.e.we a space-based intelligent computing infrastructure, completing the on-orbit validation and application of the basic functions of space computing, such as chain building, networking and cloud formation of the space computing system.
Zhao Hongjie, executive vice president of Guoxing Aerospace said arithmetic satellites are not only of great importance in promoting the development of space technology, such as providing critical arithmetic support for long-term goals such as near-Earth orbit (NEO) spacecraft, moon and Mars exploration, but also open up new possibilities for large-scale arithmetic validation and support for ground-based and low-altitude scenarios in the future.
By enabling real-time on-orbit data processing, the facility aims to overcome the efficiency bottlenecks of traditional satellite data management and promote the application and development of artificial intelligence in space, Wang Jian said.
The project reflects China's growing ambitions to extend its computing power into space, an emerging frontier that could eventually complement terrestrial cloud infrastructure and support data-intensive applications like AI and remote sensing.
Potential Applications
The applications for a space computing satellite constellation are vast and include:
Advanced Earth Observation: Real-time analysis of imagery and sensor data for environmental monitoring, urban planning, and agricultural management.
Improved Disaster Response: Rapid processing of data to assess damage and coordinate relief efforts.
Enhanced Navigation and Positioning: More accurate and resilient navigation systems.
Scientific Research: In-orbit processing of astronomical and other scientific data.
Autonomous Spacecraft Operations: Enabling more sophisticated AI-driven decision-making for spacecraft.
Communication Networks: Supporting more efficient and robust communication services.
.