Cyber Attack Estimation of Nonlinear DC Microgrids with Noisy Measurements: Spherical Simplex Radial CKF Approach

Kardan, Mohammad Amin; Moshiri, Behzad; Vafamand, Navid; Razavi–Far, Roozbeh; Saif, Mehrdad

doi:10.1109/eeeic/icpseurope51590.2021.9584647

Cited by 2 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For higher-order DC microgrids with a large number of sources and constant power loads (CPLs), the proposed CKF method is resilient against system uncertainty and noisy surroundings and has a short computing time. Likewise, a similar study was performed in [19] for microgrid state estimation under cyberattack using spherical simplex radial cubature Kalman filter (SSRCKF).…”

Section: Related Workmentioning

confidence: 99%

State Estimation Fusion for Linear Microgrids over an Unreliable Network

et al. 2022

Self Cite

View full text Add to dashboard Cite

Microgrids should be continuously monitored in order to maintain suitable voltages over time. Microgrids are mainly monitored remotely, and their measurement data transmitted through lossy communication networks are vulnerable to cyberattacks and packet loss. The current study leverages the idea of data fusion to address this problem. Hence, this paper investigates the effects of estimation fusion using various machine-learning (ML) regression methods as data fusion methods by aggregating the distributed Kalman filter (KF)-based state estimates of a linear smart microgrid in order to achieve more accurate and reliable state estimates. This unreliability in measurements is because they are received through a lossy communication network that incorporates packet loss and cyberattacks. In addition to ML regression methods, multi-layer perceptron (MLP) and dependent ordered weighted averaging (DOWA) operators are also employed for further comparisons. The results of simulation on the IEEE 4-bus model validate the effectiveness of the employed ML regression methods through the RMSE, MAE and R-squared indices under the condition of missing and manipulated measurements. In general, the results obtained by the Random Forest regression method were more accurate than those of other methods.

show abstract

Section: Related Workmentioning

confidence: 99%