Research on Photovoltaic Output Power Forecasting Based on an Attention-Enhanced BiGRU Optimized by an Improved Marine Predators Algorithm
Open Access
Abstract
Accurate photovoltaic (PV) output power forecasting is essential for reliable power system operation, yet rapidly changing meteorological conditions often degrade forecasting accuracy. This study proposes an attention-enhanced bidirectional gated recurrent unit (BiGRU) optimized by an improved Marine Predators Algorithm (IMPA) for PV output power forecasting. Kernel Principal Component Analysis (KPCA) is first employed to extract compact nonlinear representations and suppress redundant features. Then, a dual multi-head self-attention mechanism is integrated before and after the BiGRU layer to strengthen temporal feature learning under fluctuating weather. Finally, the IMPA is designed to improve exploration–exploitation balance and automatically optimize key hyperparameters. Experiments under sunny, cloudy, and rainy conditions demonstrate that IMPA-Att-BiGRU reduces MAE and RMSE by 35.7–58.5% and 22.8–49.1% versus BiGRU, respectively, while increasing R2 by 2.2–4.1 percentage points. Against the best benchmark (LSTM), MAE and RMSE are further reduced by 38.1–49.5% and 33.8–52.4%. Moreover, in a cross-day rolling forecasting test with fivefold results, IMPA-Att-BiGRU achieves 62.4% MAE and 49.3% RMSE reductions over BiGRU, confirming robust performance under long-horizon error accumulation.Keywords
Funding Information
- Digital Factory Management and Control Technology R&D Center (6025310013PQ)
- Shenzhen Polytechnic University Research Fund (6025310056K)
This publication has 30 references indexed in Scilit:
- CPWformer-DEC: improved Transformer with class-priority weather attention and dynamic error compensation for photovoltaic power forecastingExpert Systems with Applications, 2025
- Feature-enhanced multivariate ensemble model for PV power spatio-temporal forecasting and scenario generationApplied Soft Computing, 2025
- CRAformer: A cross-residual attention transformer for solar irradiation multistep forecastingEnergy, 2025
- Role-oriented binary grey wolf optimizer using foraging-following and Lévy flight for feature selectionApplied Mathematical Modelling, 2023
- A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systemsApplied Energy, 2022
- Forecasting and uncertainty analysis of day-ahead photovoltaic power using a novel forecasting methodApplied Energy, 2021
- Parameter estimation of photovoltaic models using an improved marine predators algorithmEnergy Conversion and Management, 2021
- Marine Predators Algorithm: A nature-inspired metaheuristicExpert Systems with Applications, 2020
- Feature selection using binary grey wolf optimizer with elite-based crossover for Arabic text classificationNeural Computing and Applications, 2019
- A novel robust data reconciliation method for industrial processesControl Engineering Practice, 2019