Document Type

Journal Article

Publication Title

Electric Power Systems Research

Volume

238

Publisher

Elsevier

School

School of Engineering

RAS ID

77167

Funders

Edith Cowan University

Comments

Qays, M. O., Ahmad, I., Habibi, D., & Masoum, M. A. (2025). Forecasting data-driven system strength level for inverter-based resources-integrated weak grid systems using multi-objective machine learning algorithms. Electric Power Systems Research, 238. https://doi.org/10.1016/j.epsr.2024.111112

Abstract

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.

DOI

10.1016/j.epsr.2024.111112

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

 
COinS