Zhao, JunboHuang, CanMili, Lamine M.Zhang, YingchenMin, Liang2024-01-222024-01-22202097817281310302167-9665https://hdl.handle.net/10919/117515Due to the lack of sufficient online measurements for distribution system observability, pseudo-measurements from short-term load or distributed renewable energy resources (DERs) forecasting are used. However, the accuracy of them is low and thus significantly limits the performance of distribution system state estimation (DSSE). In this paper, a robust DSSE that integrates multi-source measurement data is proposed. Specifically, the historical low-voltage (LV) side smart meters are used to forecast load and DERs injections via the support vector machine (SVM) with optimally tuned parameters. By contrast, the online smart meters at LV side are utilized to derive equivalent power injections at the MV/LV transformers, yielding more accurate pseudo-measurements compared to the forecasted injections. Furthermore, to deal with bad data caused by communication loss, instrumental errors and cyber attacks, robust DSSE that relies on generalized maximum-likelihood (GM)-estimation criterion is developed. The projection statistics are developed to adjust the weights of each measurement, leading to better balance between pseudo- and real-time measurements. Numerical results conducted on modified IEEE 33-bus system with DG integration demonstrate the effectiveness and robustness of the proposed method.5 page(s)application/pdfenPublic Domain (U.S.)Distribution system state estimationmachine learningpseudo measurementreal-time measurementsmart meterLOADConference proceedinghttps://doi.org/10.1109/isgt45199.2020.9087787Mili, Lamine [0000-0001-6134-3945]