Graph-based Deep Reinforcement Learning for Wind Farm Set-Point Optimisation

Wake steering is a form of wind farm control in which upstream turbines are deliberately yawed to misalign with the free-stream wind in order to prevent their wakes from impacting turbines further downstream. This technique can give a net increase in power generated by an array of turbines compared to greedy control, but the optimisation of multiple turbine set-points under varying wind conditions can be infeasibly complex for traditional, whitebox models. In this work, a novel deep reinforcement learning method combining the standard Deep Deterministic Policy Gradient algorithm with a graph representation of potential inter-turbine wake connections was trained to apply wake steering to an array of nine turbines under varying wind directions. The method demonstrated strong performance for wind directions with large potential farm power gains. A steady-state wind farm solver was used, employing a “quasi-dynamic” approach to sampling wind directions, to achieve an additional 47 MW (6.5%) power over four wind directions compared to greedy control.