A Hybrid LSTM-GRU-PSO Model for Inertial Energy Prediction in Renewable-Rich Power Systems

View at publisher Summarise with VIRAT
Authors: Fei Kong, Min Lu, X. Steve Yao, Aopeng Li
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The rapid integration of renewable energy sources has significantly reduced power system inertia, posing critical challenges to frequency stability. Accurate inertia prediction is essential for effective inertia compensation to maintain system stability. This paper proposes a novel hybrid deep learning model for short-term inertia prediction, integrating long short-term memory (LSTM) and gated recurrent unit (GRU) networks with hyperparameters optimized via particle swarm optimization (PSO). LSTM captures long-term dependencies and low-frequency inertia trends, while GRU efficiently models short-term dynamics and high-frequency fluctuations. PSO optimizes key hyperparameters to maximize the synergistic effect of LSTM and GRU. Evaluation results show that the proposed LSTM-GRUPSO model outperforms baseline models in prediction accuracy, as quantified by mean absolute error (MAE) and root mean square error (RMSE). This improvement enables more rapid and precise inertia compensation, critical for frequency stability in high-renewable-penetration power systems.

Fields of Study & Subjects

Power System Optimization and Stability Frequency Control in Power Systems Energy Load and Power Forecasting

Publication details

Journal / source
IEEE PES International Meeting (PES IM)
Pages
1–6
Publication date
18 January 2026
Language
EN