Enhanced Short-Term PV Power Forecasting via a Hybrid Modified CEEMDAN-Jellyfish Search Optimized BiLSTM Model

Enhanced Short-Term PV Power Forecasting via a Hybrid Modified CEEMDAN-Jellyfish Search Optimized BiLSTM Model

Accurate short-term photovoltaic (PV) power forecasting is crucial for ensuring the stability and efficiency of modern power systems, particularly given the intermittent and nonlinear characteristics of solar energy. This study proposes a novel hybrid forecasting model that integrates complete ensem...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanhui Liu, Jiulong Wang, Lingyun Song, Yicheng Liu, Liqun Shen
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Energies
Subjects:
PV power
CEEMDAN
jellyfish search algorithm
BiLSTM
short-term PV forecasting
Online Access:https://www.mdpi.com/1996-1073/18/13/3581
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate short-term photovoltaic (PV) power forecasting is crucial for ensuring the stability and efficiency of modern power systems, particularly given the intermittent and nonlinear characteristics of solar energy. This study proposes a novel hybrid forecasting model that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the jellyfish search (JS) optimization algorithm, and a bidirectional long short-term memory (BiLSTM) neural network. First, the original PV power signal was decomposed into intrinsic mode functions using a modified CEEMDAN method to better capture the complex nonlinear features. Subsequently, the fast Fourier transform and improved Pearson correlation coefficient (IPCC) were applied to identify and merge similar-frequency intrinsic mode functions, forming new composite components. Each reconstructed component was then forecasted individually using a BiLSTM model, whose parameters were optimized by the JS algorithm. Finally, the predicted components were aggregated to generate the final forecast output. Experimental results on real-world PV datasets demonstrate that the proposed CEEMDAN-JS-BiLSTM model achieves an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.9785, a MAPE of 8.1231%, and an RMSE of 37.2833, outperforming several commonly used forecasting models by a substantial margin in prediction accuracy. This highlights its effectiveness as a promising solution for intelligent PV power management.
ISSN:1996-1073

Similar Items