Solar irradiation forecast enhancement using clustering based CNN-BiLSTM-attention hybrid architecture with PSO DOI
Madderla Chiranjeevi,

Akhilesh Madyastha,

A.K. Maurya

et al.

International Journal of Ambient Energy, Journal Year: 2024, Volume and Issue: 45(1)

Published: Oct. 17, 2024

Accurate solar irradiation forecasting is essential for optimising energy use. This paper presents a novel approach: the 'Clustering-based CNN-BiLSTM-Attention Hybrid Architecture with PSO'. It combines clustering, attention mechanisms, Convolutional Neural Networks (CNN), Bidirectional Long-Short Term Memory (BiLSTM) networks, and Particle Swarm Optimisation (PSO) into unified framework. Clustering categorises days groups, improving predictive capabilities. The CNN-BiLSTM model captures spatial temporal features, identifying complex patterns. PSO optimises hybrid model's hyperparameters, while an mechanism assigns probability weights to relevant information, enhancing performance. By leveraging patterns in data, proposed improves accuracy univariate multivariate analyses multi-step predictions. Extensive tests on real-world datasets from various locations show effectiveness. For example, NASA power achieves Mean Absolute Error (MAE) of 24.028 W/m2, Root Square (RMSE) 43.025 R2 score 0.984 1-hour ahead forecasting. results significant improvements over conventional methods.

Language: Английский

A multi-energy meta-model strategy for multi-step ahead energy load forecasting DOI Creative Commons
Aristeidis Mystakidis,

Evangelia Ntozi,

Paraskevas Koukaras

et al.

Electrical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 18, 2025

Language: Английский

Citations

2
Hybrid BiGRU‐CNN Model for Load Forecasting in Smart Grids with High Renewable Energy Integration DOI Creative Commons
Kaleem Ullah,

Daniyal Shakir,

Usama Abid

et al.

IET Generation Transmission & Distribution, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

ABSTRACT Integrating renewable energy sources into smart grids increases supply and demand management because are intermittent variable. To overcome this type of challenge, short‐term load forecasting (STLF) is essential for managing energy, demand‐side flexibility, the stability with integration. This paper presents a new model called BiGRU‐CNN to improve operation STLF in grids. The integrates bidirectional gated recurrent units (BiGRUs) temporal dependencies convolutional neural networks (CNNs) extract spatial patterns from consumption data. newly developed BiGRU captures past future contexts through processing, CNN component extracts high‐level features enhance accuracy prediction. compared two other hybrid models, CNN‐LSTM CNN‐GRU, on real‐world data American electric power (AEP) ISONE datasets. Simulation results show that proposed outperforms single‐step yielding root mean square error (RMSE) 121.43 123.57 (ISONE), absolute (MAE) 90.95 62.97 percentage (MAPE) 0.61% 0.41% (ISONE). For multi‐step forecasting, yields RMSE 680.02 581.12 MAE 481.12 411.20 MAPE 3.27% 2.91% can generate accurate reliable STLF, which useful massive energy‐integrated

Language: Английский

Citations

1
A Novel Hybrid Prediction Model of Air Quality Index Based on Variational Modal Decomposition and CEEMDAN-SE-GRU DOI
Chaoli Tang, Ziyu Wang, Yuanyuan Wei

et al.

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 191, P. 2572 - 2588

Published: Oct. 9, 2024

Language: Английский

Citations

4
A Comprehensive Analysis of Bitcoin Volatility Forecasting Using Time-series Econometric Models DOI
Nrusingha Tripathy, Sarbeswara Hota, Debabrata Singh

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113339 - 113339

Published: May 1, 2025

Language: Английский

Citations

0
CRAformer: a cross-residual attention transformer for solar irradiation multistep forecasting DOI

Zongbin Zhang,

Xiaoqiao Huang, Chengli Li

et al.

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135214 - 135214

Published: Feb. 1, 2025

Language: Английский

Citations

0
Transfer learning and source domain restructuring-based BiLSTM approach for building energy consumption prediction DOI
Yi Yan, Fan Wang, Chenlu Tian

et al.

International Journal of Green Energy, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 15

Published: Nov. 2, 2024

Currently, building energy consumption prediction typically relies on vast amounts of historical data. However, for newly constructed buildings, the scarcity data leads to reduced accuracy. To address this challenge, paper proposes a novel approach that integrates transfer learning with source domain reconstruction-based BiLSTM model prediction. In first stage, both and target domains are clustered into profile types using k-means. For each type in domain, most similar profiles identified Maximum Mean Discrepancy Dynamic Time Warping. The is then reconstructed by combining these based their proportions domain. Subsequently, feature extraction method EMD-CWT-Conv introduced. Empirical Mode Decomposition applied decompose filter Continuous Wavelet Transform employed extract distinctive frequency-domain time-domain features from Final predictions made fine-tuning. Experiments grocery shop school show proposed reduces Absolute Percentage Error at least 13.19% 17.67%, respectively.

Language: Английский

Citations

1
Solar irradiation forecast enhancement using clustering based CNN-BiLSTM-attention hybrid architecture with PSO DOI
Madderla Chiranjeevi,

Akhilesh Madyastha,

A.K. Maurya

et al.

International Journal of Ambient Energy, Journal Year: 2024, Volume and Issue: 45(1)

Published: Oct. 17, 2024

Accurate solar irradiation forecasting is essential for optimising energy use. This paper presents a novel approach: the 'Clustering-based CNN-BiLSTM-Attention Hybrid Architecture with PSO'. It combines clustering, attention mechanisms, Convolutional Neural Networks (CNN), Bidirectional Long-Short Term Memory (BiLSTM) networks, and Particle Swarm Optimisation (PSO) into unified framework. Clustering categorises days groups, improving predictive capabilities. The CNN-BiLSTM model captures spatial temporal features, identifying complex patterns. PSO optimises hybrid model's hyperparameters, while an mechanism assigns probability weights to relevant information, enhancing performance. By leveraging patterns in data, proposed improves accuracy univariate multivariate analyses multi-step predictions. Extensive tests on real-world datasets from various locations show effectiveness. For example, NASA power achieves Mean Absolute Error (MAE) of 24.028 W/m2, Root Square (RMSE) 43.025 R2 score 0.984 1-hour ahead forecasting. results significant improvements over conventional methods.

Language: Английский

Citations

0