Forecasting data-driven system strength level for inverter-based resources-integrated weak grid systems using multi-objective machine learning algorithms

Md Ohirul Qays

doi:10.1016/j.epsr.2024.111112

Return

Forecasting data-driven system strength level for inverter-based resources-integrated weak grid systems using multi-objective machine learning algorithms

2025-01-01

Md Ohirul Qays *

Iftekhar Ahmad

Daryoush Habibi

Mohammad A. S. Masoum

DOI：10.1016/j.epsr.2024.111112

Original

Save

View PDF

Abstract

En 中文

Shortage of grid-fault level, known as system strength inadequacy, impacts on grid instability and can lead to blackouts. System strength is generally measured by short circuit ratio index at point of coupling (POC) of inverter-based resources (IBRs) and the grid system. Nowadays, accurate knowledge of system strength forecasting for 'next day' to 'next week' duration is essential to power system operators, owing to the higher-growth of IBRs. However, releavant publications about this subject remain limited when compared with load demand, active and reactive power prediction. Therefore, a data-driven system strength forecasting scheme is presented in this paper to surmount these issues. Multi-objective machine learning (MOML) algorithms are used to obtain the best result. The designed model uses energy management system (EMS) to collect historical online data and complete the training and testing procedures via learning frameworks such as Hedge-backpropagation neural network-based tangent function (Hedge-BPNNT), support vector machine (SVM) and long short-term memory (LSTM). The methodology is developed to predict up to seven days of system strength forecasting levels by using the last thirty-days data status. The designed model is tested on both simulated and experimented cases, confirming higher accuracy performance with reduced computational time when compared to existing literature.

Keywords:

Forecasting

Hedge-backpropagation

Inverter-based resource

Machine learning

Synchronous condenser

System strength

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.