Economic Load Forecasting based on IPSO-VMD-DBiLSTM Network
Year: 2024
Type: article
Abstract: Accurate short-term load forecasting is vital for the stable operation of power systems. Given the highly volatile and nonlinear nature of load sequences, we propose a novel Deep Bidirectional Long Short-Term Memory (DBiLSTM) network incorporating Variational Mode Decomposition (VMD) and an attention mechanism to address the aforementioned challenges. In this study, the model's hyperparameters are optimized using an Improved Particle Swarm Optimization (IPSO) technique. Notably, IPSO employs a nonlinearly decreasing inertia weight to overcome the drawbacks of premature convergence and local optima.
Author: Jiaqi Yao
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4402203075