Magnetic control of tokamak plasmas through deep reinforcement learning.

Nuclear fusion using magnetic confinement, in particular in the tokamak configuration, is a promising path towards sustainable energy. A core challenge is to shape and maintain a high-temperature plasma within the tokamak vessel. This requires high-dimensional, high-frequency, closed-loop control using magnetic actuator coils, further complicated by the diverse requirements across a wide range of plasma configurations. In this work, we introduce a previously undescribed architecture for tokamak magnetic controller design that autonomously learns to command the full set of control coils. This architecture meets control objectives specified at a high level, at the same time satisfying physical and operational constraints. This approach has unprecedented flexibility and generality in problem specification and yields a notable reduction in design effort to produce new plasma configurations. We successfully produce and control a diverse set of plasma configurations on the Tokamak à Configuration Variable1,2, including elongated, conventional shapes, as well as advanced configurations, such as negative triangularity and 'snowflake' configurations. Our approach achieves accurate tracking of the location, current and shape for these configurations. We also demonstrate sustained 'droplets' on TCV, in which two separate plasmas are maintained simultaneously within the vessel. This represents a notable advance for tokamak feedback control, showing the potential of reinforcement learning to accelerate research in the fusion domain, and is one of the most challenging real-world systems to which reinforcement learning has been applied.

Handling technology of Mega-Watt millimeter-waves for optimized heating of fusion plasmas.

Millimeter-wave components were re-examined for high power (Mega-Watt) and steady-state (greater than one hour) operation. Some millimeter-wave components, including waveguide joints, vacuum pumping sections, power monitors, sliding waveguides, and injection windows, have been improved for high power CW (Continuous Waves) transmission. To improve transmission efficiency, information about the wave phase and mode content of high power millimeter-waves propagating in corrugated waveguides, which are difficult to measure directly, were obtained by a newly developed method based on retrieved phase information. To optimize the plasma heating efficiency, a proof-of-principle study of the injection polarization feedback control was performed in the low power test stand.