System Strength Assessment Based on Multi-task Learning

Increase in permeability of renewable energy sources(RESs)leads to the prominent problem of voltage stability in power system,so it is urgent to have a system strength evaluation method with both accuracy and practicability to control its access scale within a reasonable range.Therefore,a hybrid intelligence enhancement method is proposed by combining the advantages of mechanism method and data driven method.First,calculation of critical short circuit ratio(CSCR)is set as the direction of intelligent enhancement by taking the multiple renewable energy station short circuit ratio as the quantitative indicator.Then,the construction process of CSCR dataset is proposed,and a batch simulation program of samples is developed accordingly,which provides a data basis for subsequent research.Finally,a multi-task learning model based on progressive layered extraction is used to simultaneously predict CSCR of each RESs connection point,which significantly reduces evaluation error caused by weak links.Predictive performance and anti-noise performance of the proposed method are verified on the CEPRI-FS-102 bus system,which provides strong technical support for real-time monitoring of system strength.

State Key Laboratory of Power Grid Safety and Energy Conservation,China Electric Power Research Institute,Beijing,China

The power system is experiencing a higher penetration of renewable energy generations(REGs).The short circuit ratio(SCR)and the grid impedance ratio(GIR)are two indices to quantify the system strength of the power system with REGs.In this paper,the critical short circuit ratio(CSCR)is defined as the corresponding SCR when the system voltage is in the critical stable state.Through static voltage stability analysis,the mathematical expression of the CSCR considering the impact of GIR is derived.The maximum value of CSCR is adopted as the critical value to distinguish the weak power system.Based on the static equivalent circuit analysis,it is proved that the CSCR is still effective to evaluate critical system strength considering the interactive impact among REGs.Finally,we find that the GIR can be neglected and the SCR can be used individually to evaluate the system strength when SCR>2 or GIR>5.The correctness and rationality of the CSCR and its critical value are validated on ADPSS.