RichardFindlay / wind-farm-wake-steering-optimisation-with-rl

Using q-learning to optimise offshore wind farm power generation as a wake-steering optimisation framework.
1 stars 0 forks source link

I'm sorry to bother you with a few questions. #1

Open KeosWang opened 1 year ago

KeosWang commented 1 year ago

I came across your research work "wind-farm-wake-steering-optimisation-with-rl" on GitHub (also presented in paper "A Distributed Reinforcement Learning Yaw Control Approach for Wind Farm Energy Capture Maximization") and was impressed by the work you have done. However, I have a couple of further questions related to your work.

Firstly, I was wondering if the layout of the wind farm (i.e., the number of wind turbines and their positions) can be changed? For example, can you run the simulation with a 3x3 wind farm instead of the 1x3 wind farm used in the original study?

Secondly, I was wondering if it would be possible to include control variables such as wind turbine speed and pitch angle commands in the RL algorithm? This would allow for more fine-grained control of the wind farm and could potentially lead to even better performance.

Thirdly, when I run the code 'train.py', the generated graphs do not have wind power, wind speed, angles, and turbine power, and I would like to ask what I should do in order to achieve what you have done in the visualisations folder.

I would be grateful if you could let me know your thoughts on these questions. Thank you for your time and consideration.

hao-user commented 1 month ago

Hello, take the liberty of asking if the problem you mentioned above has been solved image

hao-user commented 1 month ago

Thank you very much for your reply