Safety factor profile control with reduced central solenoid flux consumption during plasma current ramp-up phase using a reinforcement learning technique

2019 ◽  
Vol 59 (6) ◽  
pp. 066022 ◽  
Author(s):  
T. Wakatsuki ◽  
T. Suzuki ◽  
N. Hayashi ◽  
N. Oyama ◽  
S. Ide
Keyword(s):  
Reinforcement Learning ◽  
Safety Factor ◽  
Plasma Current ◽  
Current Ramp ◽  
Profile Control ◽  
Learning Technique ◽  
Flux Consumption

scholarly journals Investigation of Ideal-MHD Stable Scenario for Plasma Current Ramp-Up with No Magnetic Flux Consumption in JT-60SA

2016 ◽  
Vol 11 (0) ◽  
pp. 2403068-2403068 ◽  
Author(s):  
Takuma WAKATSUKI ◽  
Takahiro SUZUKI ◽  
Nobuhiko HAYASHI ◽  
Junya SHIRAISHI ◽  
Shunsuke IDE ◽  
...  
Keyword(s):  
Magnetic Flux ◽  
Plasma Current ◽  
Current Ramp ◽  
Ideal Mhd ◽  
Flux Consumption

Simulation of plasma current ramp-up with reduced magnetic flux consumption in JT-60SA

2015 ◽  
Vol 57 (6) ◽  
pp. 065005 ◽  
Author(s):  
T Wakatsuki ◽  
T Suzuki ◽  
N Hayashi ◽  
J Shiraishi ◽  
S Ide ◽  
...  
Keyword(s):  
Magnetic Flux ◽  
Plasma Current ◽  
Current Ramp ◽  
Flux Consumption

Study of plasma disruptions and their suppression by a fast-ramping current in the STOR-1M tokamak

1990 ◽  
Vol 68 (4-5) ◽  
pp. 369-375 ◽  
Author(s):  
A. Sarkissian ◽  
A. Hirose ◽  
W. Zhang ◽  
K. Mark ◽  
H. M. Skarsgard
Keyword(s):  
Safety Factor ◽  
Growth Time ◽  
Plasma Current ◽  
Plasma Surface ◽  
Tearing Modes ◽  
Current Ramp ◽  
Maximum Current

Minor and major disruptions, preceded by the growth of m = 2 and m = 3 modes, are observed during normal discharges on the STOR-1M tokamak, when the plasma safety factor on the plasma surface, q(a), becomes lower than 3 or with strong gas-puffing. It has been demonstrated that stable low-q discharges, with q(a) as low as 1.6 can be obtained and maintained for durations longer than the growth time for resistive tearing modes, if the plasma current is ramped up rapidly through a disruptive q region defined by 1.85 < q(a) < 2.1. The boundaries of the disruptive q region do not change when the maximum current ramp-up rate is varied between 0.5–2 kA μs−1.

Reduction of poloidal magnetic flux consumption during plasma current ramp-up in DEMO relevant plasma regimes

2016 ◽  
Vol 57 (1) ◽  
pp. 016015 ◽  
Author(s):  
T. Wakatsuki ◽  
T. Suzuki ◽  
N. Hayashi ◽  
J. Shiraishi ◽  
Y. Sakamoto ◽  
...  
Keyword(s):  
Magnetic Flux ◽  
Plasma Current ◽  
Current Ramp ◽  
Flux Consumption

scholarly journals Computation offloading through mobile vehicles in IoT-edge-cloud network

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Jun Long ◽  
Yueyi Luo ◽  
Xiaoyu Zhu ◽  
Entao Luo ◽  
Mingfeng Huang
Keyword(s):  
Reinforcement Learning ◽  
Energy Consumption ◽  
Low Cost ◽  
Computation Offloading ◽  
Mobile Edge Computing ◽  
Challenging Problem ◽  
Learning Technique ◽  
Cloud Network ◽  
The City ◽  
Task Offloading

AbstractWith the developing of Internet of Things (IoT) and mobile edge computing (MEC), more and more sensing devices are widely deployed in the smart city. These sensing devices generate various kinds of tasks, which need to be sent to cloud to process. Usually, the sensing devices do not equip with wireless modules, because it is neither economical nor energy saving. Thus, it is a challenging problem to find a way to offload tasks for sensing devices. However, many vehicles are moving around the city, which can communicate with sensing devices in an effective and low-cost way. In this paper, we propose a computation offloading scheme through mobile vehicles in IoT-edge-cloud network. The sensing devices generate tasks and transmit the tasks to vehicles, then the vehicles decide to compute the tasks in the local vehicle, MEC server or cloud center. The computation offloading decision is made based on the utility function of the energy consumption and transmission delay, and the deep reinforcement learning technique is adopted to make decisions. Our proposed method can make full use of the existing infrastructures to implement the task offloading of sensing devices, the experimental results show that our proposed solution can achieve the maximum reward and decrease delay.

scholarly journals Applying a Deep Q Network for OpenAIs Car Racing Game

2020 ◽  
Author(s):  
Ali Fakhry
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
State Of The Art ◽  
Learning Techniques ◽  
Car Racing ◽  
Custom Made ◽  
Learning Technique ◽  
Reward Threshold

The applications of Deep Q-Networks are seen throughout the field of reinforcement learning, a large subsect of machine learning. Using a classic environment from OpenAI, CarRacing-v0, a 2D car racing environment, alongside a custom based modification of the environment, a DQN, Deep Q-Network, was created to solve both the classic and custom environments. The environments are tested using custom made CNN architectures and applying transfer learning from Resnet18. While DQNs were state of the art years ago, using it for CarRacing-v0 appears somewhat unappealing and not as effective as other reinforcement learning techniques. Overall, while the model did train and the agent learned various parts of the environment, attempting to reach the reward threshold for the environment with this reinforcement learning technique seems problematic and difficult as other techniques would be more useful.

Sign in / Sign up

Export Citation Format

Share Document