Augmented random search based inter-area oscillation damping using high voltage DC transmission

The high voltage DC (HVDC) Transmissions are under rapid development all over the world. The HVDC transmission not only provides a low-loss electric energy transfer path, but also acts as an alternative tool for damping inter-area oscillations in modern electric power systems. In this paper, we proposed a novel reinforcement learning based HVDC oscillation damping controller using the augmented random search (ARS) algorithm. By leveraging the wide-area information such as voltages, phase angle, machine speeds, the ARS was able to determine the modulation power of HVDC to effectively damp inter-area oscillations. The proposed research overcomes the challenges of setting optimal controller parameters of the HVDC under various system transient events. The proposed ARS-based HVDC power oscillation damping control approach was tested on a simplified Western American large-scale power system model called minniWECC. Extensive studies have demonstrated the superiority of the proposed ARS-based HVDC control approach over conventional power oscillation damping methods.

Automated summary

This paper proposes a novel reinforcement learning based HVDC oscillation damping controller using the augmented random search (ARS) algorithm, which leverages wide-area information to effectively damp inter-area oscillations.