NASA spacecrafts, which typically rely on human-controlled radio systems to communicate with Earth, are now looking at cognitive radios — the infusion of artificial intelligence into space communications networks — to meet demand and increase efficiency.
Specific portions of the electromagnetic spectrum used for communications to various users. However, such channels are limited in number and can cause a bottleneck in the era of increasing communications.
Software-defined radios such as cognitive radio use artificial intelligence to employ underutilised portions of the electromagnetic spectrum without human intervention. These “white spaces” are currently unused (but already licensed) segments of the spectrum. The US Federal Communications Commission (FCC) permits a cognitive radio to use the frequency while unused by its primary user until the user becomes active again.
Janette C Briones, principal investigator in the cognitive communication project at NASA’s Glenn Research Center in Cleveland, Ohio, said, “Modern space communications systems use complex software to support science and exploration missions. By applying artificial intelligence and machine learning, satellites control these systems seamlessly, making real-time decisions without awaiting instruction.”
Briones added, “The recent development of cognitive technologies is a new thrust in the architecture of communications systems. We envision these technologies will make our communications networks more efficient and resilient for missions exploring the depths of space. By integrating artificial intelligence and cognitive radios into our networks, we will increase the efficiency, autonomy and reliability of space communications systems.”
In the future, a NASA cognitive radio could even learn to shut itself down temporarily to mitigate radiation damage during severe space weather events. Adaptive radio software could circumvent the harmful effects of space weather, increasing science and exploration data returns. A cognitive radio network could also suggest alternate data paths to the ground. These processes could prioritise and route data through multiple paths simultaneously to avoid interference. The cognitive radio’s artificial intelligence could also allocate ground station downlinks just hours in advance, as opposed to weeks, leading to more efficient scheduling.
Additionally, cognitive radio may make communications network operations more efficient by decreasing the need for human intervention. An intelligent radio could adapt to new electromagnetic landscapes without human help and predict common operational settings for different environments, automating time-consuming processes previously handled by humans.
Try deep learning using MATLAB