SinoGreenTech Academic Portal
Official PDF TranslationPower Automation Equipment

Data-Driven Regression-Based Transient Equivalent Modeling of Transmission Networks with High Renewable Energy Penetration

Authors: LIU Xiangshang; WANG Huifang; LIU Dongran; DAI Shiqiang; MA Wei

DOI: 10.16081/j.epae.202606023Status: Verified Translated Edition
Sponsored AdvertisementAd Placement Area
reCAPTCHA Bot Shield Active

Preparing Secure Academic Download

Verifying human reader & generating high-resolution document...

Verifying Document Integrity15s remaining
← Back to Article
Protected by Google reCAPTCHA v3.PrivacyTerms
Sponsored ContentAdSense In-Feed Ad Slot

Key Findings in This Report

• • The proposed model reduces short-circuit current calculation errors by up to 40% compared to the conventional Thévenin equivalent, as validated on the modified IEEE 39-bus system with high renewable penetration, directly improving protection coordination and equipment sizing in distribution networks. • • Renewable generators enter LVRT when point-of-common-coupling voltage drops below 0.9 p.u., injecting reactive current up to 1.2 times rated current (K2=1.2) and limiting active current to zero at voltages below 0.458 p.u. (for K1=1.5), creating non-smooth response curves that cause gradient-based iterative algorithms to fail near inflection points. • • The data-driven regression model establishes a nonlinear mapping between the additional short-circuit impedance (RO, XO) and equivalent parameters (RS, XS, and VCCS control function), enabling accurate parameter estimation without iterative convergence issues, with offline training on simulation data and online application requiring only fault features. • • The VCCS control function F(nE, U) explicitly accounts for the number of renewable generators entering LVRT (nE) and boundary voltage U, capturing the aggregate transient behavior of all renewable units—both in LVRT and normal operation—thereby extending the model's validity across varying fault locations and operating conditions.