Research on a novel photovoltaic power forecasting model based on parallel long and short-term time series network

Energy, Journal Year: 2024, Volume and Issue: 293, P. 130621 - 130621

Published: Feb. 10, 2024

Language: Английский

---

An adaptive distribution-matched recurrent network for wind power prediction using time-series distribution period division

Energy, Journal Year: 2024, Volume and Issue: 299, P. 131383 - 131383

Published: April 25, 2024

Language: Английский

---

Research on Indoor Environment Prediction of Pig House Based on OTDBO–TCN–GRU Algorithm

Animals, Journal Year: 2024, Volume and Issue: 14(6), P. 863 - 863

Published: March 11, 2024

Temperature and humidity, along with concentrations of ammonia hydrogen sulfide, are critical environmental factors that significantly influence the growth health pigs within porcine habitats. The ability to accurately predict these variables in pig houses is pivotal, as it provides crucial decision-making support for precise targeted regulation internal conditions. This approach ensures an optimal living environment, essential well-being healthy development pigs. existing methodologies forecasting currently hampered by issues low predictive accuracy significant fluctuations To address challenges this study, a hybrid model incorporating improved dung beetle algorithm (DBO), temporal convolutional networks (TCNs), gated recurrent units (GRUs) proposed prediction optimization barns. enhances global search capability DBO introducing Osprey Eagle (OOA). uses initially fit time-series data factors, subsequently combines long-term dependence capture TCNs non-linear sequence processing GRUs residuals fit. In concentration, OTDBO–TCN–GRU shows excellent performance mean absolute error (MAE), square (MSE), coefficient determination (R2) 0.0474, 0.0039, 0.9871, respectively. Compared DBO–TCN–GRU model, achieves reductions 37.2% 66.7% MAE MSE, respectively, while R2 value 2.5%. OOA achieved 48.7% 74.2% MSE metrics, 3.6%. addition, has less than 0.3 mg/m3 gases compared other algorithms, on sudden changes, which robustness adaptability prediction. Therefore, optimizes factor time series offers substantial decision control houses.

Language: Английский

---

BiLSTM-InceptionV3-Transformer-fully-connected model for short-term wind power forecasting

Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 321, P. 119094 - 119094

Published: Sept. 25, 2024

Language: Английский

---

A novel link prediction model for interval-valued crude oil prices based on complex network and multi-source information

Applied Energy, Journal Year: 2024, Volume and Issue: 376, P. 124261 - 124261

Published: Aug. 27, 2024

Language: Английский

---

Probabilistic prediction of wind farm power generation using non-crossing quantile regression

Control Engineering Practice, Journal Year: 2025, Volume and Issue: 156, P. 106226 - 106226

Published: Jan. 5, 2025

Language: Английский

---

Feature fusion temporal convolution: Wind power forecasting with light hyperparameter optimization

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 2468 - 2481

Published: Feb. 8, 2025

Language: Английский

---

Improved wavelet threshold denoising method for magnetic field signals of magnetic targets

Measurement Science and Technology, Journal Year: 2025, Volume and Issue: 36(3), P. 036105 - 036105

Published: Feb. 10, 2025

Abstract The presence of complex electromagnetic noise significantly impacts the accuracy magnetic targets signal detection, necessitating development an effective denoising method to enhance detection precision. Nevertheless, traditional methods faces problems such as difficulty in selecting wavelet basis, specifying decomposition level, and unreasonable selection thresholds. This study introduces improved threshold based on peak-to-sum ratio composite evaluation index T, named (PSR-T-IWTD). PSR-T-IWTD integrates basis method, level function design method. Calculate T select with smallest optimal basis. number is determined by PSR detail coefficients. An are introduced further performance (WTD). Finally, field test ship model was designed compared Butterworth low-pass filter (BLPF), adaptive (OWSWATD) WTD (T-IWTD) verify effectiveness PSR-T-IWTD. results show that has lower computational complexity. Meanwhile, improves signal-to-noise 10.2%, 6.8% 8.3% BLPF, OWSWATD T-IWTD, respectively.

Language: Английский

---

A point-interval wind speed prediction model based on entropy clustering and hybrid optimization weighted strategy

Renewable Energy, Journal Year: 2025, Volume and Issue: unknown, P. 122653 - 122653

Published: Feb. 1, 2025

Language: Английский

---

Short-Term Wind Power Prediction Method Based on CEEMDAN-VMD-GRU Hybrid Model

Energies, Journal Year: 2025, Volume and Issue: 18(6), P. 1465 - 1465

Published: March 17, 2025

In order to improve wind power prediction accuracy and increase the utilization of power, this study proposes a novel complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)–variational modal (VMD)–gated recurrent unit (GRU) model. With goal extracting feature information that existed in temporal series data, CEEMDAN VMD are used divide raw data into several intrinsic function components. Furthermore, reduce computational burden enhance convergence speed, these (IMF) components integrated rebuilt via results sample entropy K-means. Lastly, ensure completeness outcomes, final synthesized through superposition all IMF The simulation indicate proposed model is superior other models robustness.

Language: Английский

---