Robust mapping rule estimation for power flow analysis in distribution grids

A Support Vector Regression Based Model Predictive Control for Volt-Var Optimization of Distribution Systems

“…which should be selected based on the application. It is suggested, in [12], to use a polynomial function as the nonlinear kernel for mapping power flow equations. However, our simulation results that are presented in the next section showed that Gaussian function could predict voltage profiles with higher accuracy than polynomial kernel.…”

“…The power flow model is built based on physical configuration of the distribution grid and its parameters with the assumption that such data is accurate. In many primary and secondary distribution grids this is not the case [12], due to the fact that power utilities have limited information about their distribution networks. Vast numbers of distribution feeders, limited data on secondary networks and unbalanced loads are factors that contribute to such limited knowledge of distribution data [11].…”

“…An example of a data-driven approach is [14] where linear regression is used to build a linearized model of the distribution network. The effectiveness of Support Vector Regression (SVR) in modeling power flow equations of distribution systems is proven in [12]. The kernel trick [15] used in the mentioned study allows the SVR model to handle the nonlinearity of system power flow and to incorporate active controllers of DERs in the regression model.…”

“…The kernel trick [15] used in the mentioned study allows the SVR model to handle the nonlinearity of system power flow and to incorporate active controllers of DERs in the regression model. Data-driven models presented in [14] and [12] have a strong potential to be employed in the VVO problem. Such potential has been comprehensively reviewed in [16] from technical and security points of view.…”

Transmission Contingency Analysis Based on Data-Driven Equivalencing of Radial Distribution Networks Considering Uncertainties

“…Particularly, it discusses the data-driven schemes in the operation of smart grids. Also, some researchers have introduced data-driven approaches to handle with traditional applications in power system operations, such as state estimation [13], topology or parameter identification [14]- [16], power flow [17], optimal power flow [18], unit commitment [19], etc. However, this important technology has not been utilized in TN-DN coordinated analysis.…”