Reduced-dimensional skip-inception feature-aggregated classified proportional-integral-derivative for suppression of mixed-mode oscillations in hydropower units

• Published in: Electric power systems research Vol. 225; p. 109874
• Main Authors: Yin, Linfei, Fan, Boling
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2023
• Subjects: Dimensionality reduction; Feature aggregation; Governor parameters; Oscillation modes; Skip connection; Dimensionality reduction; Oscillation modes; Skip connection; Governor parameters; Feature aggregation
• ISSN: 0378-7796; 1873-2046
• DOI: 10.1016/j.epsr.2023.109874

•Classification of low-frequency and ultra-low-frequency oscillations are considered.•The primary frequency regulation model of hydropower unit is built.•A reduced-dimensional skip-inception feature-aggregated network model is proposed.•The network model solves the imprecise identification of multiple oscillation modes.•Oscillations are suppressed by classified controllers with classification results. The existing methods cannot effectively distinguish and suppress mixed-mode oscillations in hydro-dominated grid operation caused by different factors. This work proposes a reduced-dimensional skip-inception feature-aggregated classified proportional-integral-derivative to solve the imprecise identification and suppression of multiple oscillation modes. The reduced-dimensional skip-inception feature-aggregated network (RSFN) of the proposed controller classifies mixed-mode oscillations accurately. The RSFN introduces a skip connection on the modified Inception module to solve the problem of model degradation and accuracy reduction caused by increasing network depth. Meanwhile, the dimensionality reduction and feature aggregation of RSFN reduce the computation memory and improve the performance of the network. This work classifies different oscillation modes by the proposed network model and adopts appropriate governor parameters according to the classification results to suppress oscillations. The RSFN performs better than other network models and can accurately distinguish the oscillation modes.