Weighted least-square support vector machine(WLS-SVM)is proposed in this research as a real-time transient stability evaluation method using the synchrophasor measurement received from phasor measurement units(PMUs).T...Weighted least-square support vector machine(WLS-SVM)is proposed in this research as a real-time transient stability evaluation method using the synchrophasor measurement received from phasor measurement units(PMUs).This method considers the directional overcurrent relays(DOCRs)for the transmission system,whereas in previous studies,the effect of protective mechanisms on the transient stability was largely ignored.When protective relays are activated in power system,the configuration of the power system is altered to mitigate the risk of the power system becoming unstable.The present study considers the operation of DOCRs in transmission lines for the transient stability so that the proposed method can respond to changes in the configuration of the case study system.In addition,WLS-SVM is employed for an online assessment of the transient stability.WLS-SVM not only is effective in response due to its faster speed,but also is resistant to noise and has excellent performance against the measurement errors of PMUs.To extract the characteristics of the vectors that are fed into the WLS-SVM algorithm,principal component analysis is used.The findings of the suggested technique reveal that it has higher accuracy and optimum performance,as compared to the extreme learning machine method,the adaptive neuro-fuzzy inference system method,and the back-propagation neural network method.The proposed technique is validated in the New England 39-bus system and the IEEE 118-bus system.展开更多
When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatmen...When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatment. Existing approaches include directly modelling clinical outcomeby defining the optimal treatment rule according to the interactions between treatment andcovariates and outcome weighted approach that uses clinical outcome as weights to maximise atarget function whose value directly reflects correct treatment assignment. All existing articles ofestimating individualised treatment rules are all assuming just two treatment assignments. Herewe propose an outcome weighted learning approach that uses a vector hinge loss to extend estimating individualised treatment rules in multi-category treatments case. The consistency of theresulting estimator is shown. We also demonstrate the performance of our approach in simulationstudies and a real data analysis.展开更多
文摘Weighted least-square support vector machine(WLS-SVM)is proposed in this research as a real-time transient stability evaluation method using the synchrophasor measurement received from phasor measurement units(PMUs).This method considers the directional overcurrent relays(DOCRs)for the transmission system,whereas in previous studies,the effect of protective mechanisms on the transient stability was largely ignored.When protective relays are activated in power system,the configuration of the power system is altered to mitigate the risk of the power system becoming unstable.The present study considers the operation of DOCRs in transmission lines for the transient stability so that the proposed method can respond to changes in the configuration of the case study system.In addition,WLS-SVM is employed for an online assessment of the transient stability.WLS-SVM not only is effective in response due to its faster speed,but also is resistant to noise and has excellent performance against the measurement errors of PMUs.To extract the characteristics of the vectors that are fed into the WLS-SVM algorithm,principal component analysis is used.The findings of the suggested technique reveal that it has higher accuracy and optimum performance,as compared to the extreme learning machine method,the adaptive neuro-fuzzy inference system method,and the back-propagation neural network method.The proposed technique is validated in the New England 39-bus system and the IEEE 118-bus system.
基金The author would like to thank Jun Shao and Menggang Yu for their help with preparing the manuscript.This work was supported by the Chinese 111 Project[grant number B14019](for Lou and Shao).
文摘When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatment. Existing approaches include directly modelling clinical outcomeby defining the optimal treatment rule according to the interactions between treatment andcovariates and outcome weighted approach that uses clinical outcome as weights to maximise atarget function whose value directly reflects correct treatment assignment. All existing articles ofestimating individualised treatment rules are all assuming just two treatment assignments. Herewe propose an outcome weighted learning approach that uses a vector hinge loss to extend estimating individualised treatment rules in multi-category treatments case. The consistency of theresulting estimator is shown. We also demonstrate the performance of our approach in simulationstudies and a real data analysis.
