Machine learning technologies have been applied to improve the real-time performance of small-signal stability (SSS) assessment, while achieving a high accuracy requires numerous samples, and model performance may degrade if not updated over time. Furthermore, single models tend to learn general features without analyzing specific characteristics within the samples, which may lead to a high frequency of large errors, particularly at operating points (OPs) where the eigenvalue trajectories have sudden changes. Facing such issues, this paper introduces the concept of reference points (RPs) for accurate online tracking of the rightmost eigenvalue (RE), as the RP information reflects the characteristics among its surrounding OPs. The performance of this model is sensitive to RPs, so affinity propagation (AP) clustering is employed to determine the number of RPs and generate corresponding groups, accommodating diverse OP characteristics. This paper generates data-driven networks for each group and combines them into a multinetwork for precise RE prediction. Case studies show that the use of RPs improves accuracy by nearly 2% compared to methods without them, with even greater improvements in mixed load type scenarios. To mitigate computational stress, this paper proposes an adaptive partial update strategy based on the dynamic time warping algorithm, avoiding the need to update all networks within each sliding time window. Experimental results verify that the total running time is reduced by more than 10%. Online tracking demonstrates that RPs help decrease the frequency of large errors by 40%, especially at sudden change points of RE trajectories.

No abstract

Small-signal stability assessment (SSSA) plays a significant role in large-scale power systems operation. Since the computational burden and unavailability of the detailed time-varying model, it is practically difficult to use model-based approaches to meet the real-time demands of SSSA. Considering the neighbour eigenvalues share similar oscillation characteristics, this paper presents an efficient method for SSSA based on looking at the regions that include the neighbour eigenvalues of interest rather than the exact position of eigenvalues. After dividing the insufficient damping area into several regions, the limitations of existing data-driven SSSA resulting from the uncertainty of critical eigenvalues are overcome by virtual regional eigenvalue (VRE), which is introduced to estimate the prominent eigenvalue of neighbour eigenvalues in each divided region. A composite structure based on Long short-term memory is designed to accommodate the different number of eigenvalues, generate VRE and the boundary of eigenvalues in divided regions. The effectiveness of the proposed method is demonstrated by two different scale test systems.