Recently,we demonstrated the success of a time-synchronized state estimator using deep neural networks(DNNs)for real-time unobservable distribution systems.In this paper,we provide analytical bounds on the performance...Recently,we demonstrated the success of a time-synchronized state estimator using deep neural networks(DNNs)for real-time unobservable distribution systems.In this paper,we provide analytical bounds on the performance of the state estimator as a function of perturbations in the input mea-surements.It has already been shown that evaluating perfor-mance based only on the test dataset might not effectively indi-cate the ability of a trained DNN to handle input perturbations.As such,we analytically verify the robustness and trustworthi-ness of DNNs to input perturbations by treating them as mixed-integer linear programming(MILP)problems.The ability of batch normalization in addressing the scalability limitations of the MILP formulation is also highlighted.The framework is val-idated by performing time-synchronized distribution system state estimation for a modified IEEE 34-node system and a real-world large distribution system,both of which are incompletely observed by micro-phasor measurement units.展开更多
基金supported in part by the Department of Energy(No.DE-AR-0001001,No.DE-EE0009355)the National Science Foundation(NSF)(No.ECCS-2145063)。
文摘Recently,we demonstrated the success of a time-synchronized state estimator using deep neural networks(DNNs)for real-time unobservable distribution systems.In this paper,we provide analytical bounds on the performance of the state estimator as a function of perturbations in the input mea-surements.It has already been shown that evaluating perfor-mance based only on the test dataset might not effectively indi-cate the ability of a trained DNN to handle input perturbations.As such,we analytically verify the robustness and trustworthi-ness of DNNs to input perturbations by treating them as mixed-integer linear programming(MILP)problems.The ability of batch normalization in addressing the scalability limitations of the MILP formulation is also highlighted.The framework is val-idated by performing time-synchronized distribution system state estimation for a modified IEEE 34-node system and a real-world large distribution system,both of which are incompletely observed by micro-phasor measurement units.
