Shuaihu Li

Dr. Shuaihu Li


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2019 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
MTMao Tan
Mao Tan
SYSiping Yuan
Siping Yuan
SLShuaihu Li
Shuaihu Li
YSYongxin Su
Yongxin Su
HLHui Li
Hui Li
FHFeng He He
Feng He He
Power demand forecasting with high accuracy is a guarantee to keep the balance between power supply and demand. Due to strong volatility of industrial power load, ultra-short-term power demand is difficult to forecast accurately and robustly. To solve this problem, this paper proposes a Long Short-Term Memory (LSTM) network based hybrid ensemble learning forecasting model. A hybrid ensemble strategy---which consists of Bagging, Random Subspace, and Boosting with ensemble pruning---is designed to extract the deep features from multivariate data, and a new loss function that integrates peak demand forecasting error is proposed according to bias-variance tradeoff. Experimental results on open dataset and practical datasets show that the proposed model outperforms several state-of-the-art time series forecasting models, and obtains higher accuracy and robustness to forecast peak demand.

14 July 2022 in Frontiers in Energy Research
Verified
Journal Article
Open access
SLShuaihu Li
Shuaihu Li
XZXiang Zhao
Xiang Zhao
WLWenju Liang
Wenju Liang
THTanjid Hossain
Tanjid Hossain
ZZZhidan Zhang
Zhidan Zhang
In order to quickly obtain the voltage value of each node after the power system line is disconnected, a fast and accurate calculation method of breaking voltage based on Taylor series expansion is proposed in this study, which can calculate the value of nodal voltage of the system in a short time. At first, a breaking parameter is introduced into the admittance of the disconnected line, and a nonlinear disconnection function is constructed about the breaking parameter. After the line is disconnected, the voltage of each node and the admittance matrix of each node are functions of the relevant parameters, and then, the Taylor series is used to expand. The voltage of each node of the system before breaking is considered as the initial value of the Taylor series, and the first, second, and third derivatives of the node voltage with respect to the parameter are considered as the correction term; the voltage of each node of the system is calculated after the line is disconnected. Finally, the simulation results of the IEEE 14-node system are used to verify the correctness of the proposed method.

29 November 2017 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
SLShuaihu Li
Shuaihu Li
YTYi Tan
Yi Tan
CLCanbing Li
Canbing Li
YCYijia Cao
Yijia Cao
LJLin Jiang
Lin Jiang
Modern power system suffers voltage instability more frequently due to the increasing load. Sensitivity analysis based preventive control is widely recognized as an effective method for preventing voltage instability. However, the well-known load margin (LM) based sensitivity methods are not suitable for real-time application since they must solve the left eigenvector of zero eigenvalue of the Jacobi matrix at the critical point and require the system-wide information. Therefore, this paper proposes a fast sensitivity-based method for selecting the most effective preventive controls. The sensitivity analysis uses a local voltage stability index, i.e., load impedance modulus margin (LIMM) which is derived from the local measurements (nodal voltage and current), and the sensitivity ranking can be obtained more accurately and faster than traditional methods based on load margin. Such computational advantages make it suitable for online application. The effectiveness of the proposed method is successfully validated by both small and large-scale power systems.

14 July 2023 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
WWWeiyu Wang
Weiyu Wang
YCYijia Cao
Yijia Cao
LJLin Jiang
Lin Jiang
CCChun Chen
Chun Chen
YLYong Li
Yong Li
XSXingyu Shi
Xingyu Shi
Low-inertia power grids could suffer from large frequency excursions under even small power disturbances. When a voltage source converter-based high voltage direct current (VSC-HVDC) system is used to integrate a low-inertia grid into a main grid, an ancillary frequency support service can be provided to the low-inertia grid by the VSC-HVDC system. This paper proposes a perturbation observer-based fast frequency support controller (POFFS) of VSC-HVDC systems to improve the frequency stability of low-inertia power grids. According to the feedback linearization and the high gain observer technique, the perturbation observer of the inverter station is designed to estimate the comprehensive impact of multiple perturbations, including the power disturbances in low-inertia grids, the uncertainty of grid inertia, and unknown nonlinear dynamics. The estimate of the perturbations are further compensated by the feedback control loop to achieve robust frequency regulation. Compared with the conventional frequency controller, the proposed POFFS can provide better frequency support to low-inertia power grids, without requiring an accurate system model and parameters. Two test systems are used to verify the effectiveness of the proposed POFFS.

14 March 2019 in IEEE Access
Verified
Journal Article
Open access
YGYingcong Guo
Yingcong Guo
SLShuaihu Li
Shuaihu Li
CLCanbing Li
Canbing Li
HPHanmei Peng
Hanmei Peng

18 February 2019 in IEEE Access
Verified
Journal Article
Open access
HPHanmei Peng
Hanmei Peng
MSMin Su
Min Su
SLShuaihu Li
Shuaihu Li
CLCanbing Li
Canbing Li
Due to lack the support from the main grid, the islanded hybrid AC/DC microgrid will more likely cause the power flow severe fluctuation and even the microgrid to be split once a serious contingency occurs. To maintain the security and stability of the system under such a condition, this paper proposes a new static security risk assessment of the islanded hybrid AC/DC microgrid considering the hybrid AC/DC microgrid was split. Firstly, this paper presents a static security analysis criterion to determine the post-contingencies splitting scheme and a new load-shedding strategy to achieve power balance of subsystems. On this basis, a probabilistic power flow calculation method based on Levenberg-Marquardt with a nonmonotone line search (LMNL) algorithm is applied to calculate the probabilistic power flow of the islanded subsystems. Finally, the probability distribution of static security risk assessment indexes including the DC loss load risk, AC loss load risk, and interlinking converter (ILC) active power limit violation risk are obtained. Simulation results on the test system demonstrate the necessity of considering the hybrid AC/DC microgrid was split, and prove the feasibility and effectiveness of the proposed method.