Data-driven Robust State Estimation Through Off-line Learning and On-line Matching

To overcome the shortcomings of model-driven state estimation methods, this paper proposes a data-driven robust (DDSE) method through off-line learning and on-line matching. At stage, linear regression equation is presented by clustering historical data from supervisory control acquisition (SCADA), which provides guarantee for solving over-learning problem existing DDSE methods; then novel that can be transformed into quadratic programming (QP) models proposed to obtain mapping relationship between measurements variables (MRBMS). The QP well solve collinearity in data. Furthermore, stage greatly accelerated three aspects including reducing categories, constructing tree retrieval structure known topologies, using sensitivity analysis when models. matching quickly current snapshot with ones, corresponding MRBMS obtained, values obtained. Simulations demonstrate has obvious advantages terms suppressing problems, dealing robustness, computation efficiency.