Successfully achieving nuclear fusion promises to provide an unlimited and sustainable source of clean energy, but we can only realize this incredible dream if we can master the complex physics that take place inside the reactor.
For decades, scientists have made strides towards this goal, but many challenges remain. One of the main obstacles is to successfully control the unstable and overheated plasma in the reactor, but a new approach reveals how we can do this.
In a joint effort by EPFL’s Swiss Plasma Center (SPC) and artificial intelligence (AI) research company DeepMind, the scientists used a deep reinforcement learning (RL) to study the nuances of plasma behavior and control within a fusion tokamak, a donut-shaped device that uses a series of magnetic coils positioned around the reactor to control and manipulate the plasma within it .
It’s not an easy balancing act, as the coils require an enormous amount of subtle voltage adjustments, up to thousands of times per second, to successfully keep the plasma confined within magnetic fields.
Hence, complex, multilayer systems are needed to handle the coils to support nuclear fusion reactions, which involve keeping the plasma stable at hundreds of millions of degrees Celsius, hotter than even the Sun’s core. In a new study, however, researchers show that a single AI system can supervise the task on its own.
“Using a learning architecture that combines deep RL and a simulated environment, we have produced controllers that can both keep the plasma stable and be used to accurately sculpt it into different shapes,” the team explains in a DeepMind blog post.
To accomplish the feat, the researchers trained their artificial intelligence system in a tokamak simulator, in which the machine learning system discovered, through trial and error, how to navigate the intricacies of plasma’s magnetic confinement.
After its training window, the AI took it to the next level, applying what it had learned in the simulator in the real world. By controlling the SPC’s Variable Configuration Tokamak (TCV), the RL system sculpted the plasma into a range of different shapes within the reactor, including one that had never been seen before in the TCV: stabilizing “droplets” in which two plasmas coexisted simultaneously within the device.
In addition to conventional shapes, AI could also produce advanced configurations, sculpting the plasma into configurations of “negative triangularity” and “snowflake”.
Each of these manifestations has different types of potential for energy harvesting in the future if we can maintain nuclear fusion reactions. One of the configurations controlled by the system could hold particular promise for the future study of the International Thermonuclear Experimental Reactor (ITER), the largest nuclear fusion experiment in the world, currently under construction in France.
According to the researchers, magnetic mastery of these plasma formations represents “one of the most challenging systems in the real world to which reinforcement learning has been applied” and could set a radically new direction in how the world’s tokamaks are designed. real.
Indeed, some suggest that what we are seeing here will radically alter the future of advanced plasma control systems in fusion reactors. “This AI is, in my opinion, the only way forward,” physicist Gianluca Sarri of Queen’s University in Belfast, who was not involved in the study, told New Scientist. “There are so many variables and a small change in one of them can cause a big change in the final output. If you try to do it manually, it’s a very long process. “