An Innovative NOx Emissions Prediction Model Based on Random Forest Feature Selection and Evolutionary Reformer

Processes, Journal Year: 2025, Volume and Issue: 13(1), P. 107 - 107

Published: Jan. 3, 2025

Developing more precise NOx emission prediction models is pivotal for effectively controlling emissions from gas turbines. In this paper, a Reformer combined with random forest (RF) feature selection and the chaos game optimization (CGO) algorithm to predict in Firstly, RF evaluates importance of data features reduces dimensionality multidimensional improve predictive performance model. Secondly, model extracts inherent pattern different explores intrinsic connection between turbine variables establish accurate Thirdly, CGO parameter-free meta-heuristic used find best parameters The was improved using Chebyshev Chaos Mapping initial population quality algorithm. To evaluate efficiency proposed model, dataset turbines north-western Turkey studied, results obtained are compared seven benchmark models. final paper show that can select appropriate input variables, extract links build At same time, ICGO optimize effectively.

Language: Английский

---

TFEformer: A new temporal frequency ensemble transformer for day-ahead photovoltaic power prediction

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 448, P. 141690 - 141690

Published: March 6, 2024

Language: Английский

---

Harnessing AI for solar energy: Emergence of transformer models

Applied Energy, Journal Year: 2024, Volume and Issue: 369, P. 123541 - 123541

Published: June 1, 2024

Language: Английский

---

An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

Applied Energy, Journal Year: 2024, Volume and Issue: 377, P. 124738 - 124738

Published: Oct. 22, 2024

Language: Английский

---

Chaos Game Optimization: A comprehensive study of its variants, applications, and future directions

Computer Science Review, Journal Year: 2024, Volume and Issue: 53, P. 100647 - 100647

Published: June 7, 2024

Language: Английский

---

A Deep Learning Model for Predicting the State of Energy in Lithium-Ion Batteries Based on Magnetic Field Effects

Energy, Journal Year: 2024, Volume and Issue: 304, P. 132161 - 132161

Published: June 25, 2024

Language: Английский

---

Short-term wind power prediction based on IBOA-AdaBoost-RVM

Journal of King Saud University - Science, Journal Year: 2024, Volume and Issue: 36(11), P. 103550 - 103550

Published: Nov. 22, 2024

Language: Английский

---

Short-Term Photovoltaic Power Forecasting Based on a Feature Rise-Dimensional Two-Layer Ensemble Learning Model

Sustainability, Journal Year: 2023, Volume and Issue: 15(21), P. 15594 - 15594

Published: Nov. 3, 2023

Photovoltaic (PV) power generation has brought about enormous economic and environmental benefits, promoting sustainable development. However, due to the intermittency volatility of PV power, high penetration rate may pose challenges planning operation systems. Accurate forecasting is crucial for safe stable grid. This paper proposes a short-term method using K-means clustering, ensemble learning (EL), feature rise-dimensional (FRD) approach, quantile regression (QR) improve accuracy deterministic probabilistic power. The clustering algorithm was used construct weather categories. EL two-layer (TLEL) model based on eXtreme gradient boosting (XGBoost), random forest (RF), CatBoost, long memory (LSTM) models. FRD approach optimize TLEL model, FRD-XGBoost-LSTM (R-XGBL), FRD-RF-LSTM (R-RFL), FRD-CatBoost-LSTM (R-CatBL) models, combine them with results reciprocal error method, in order obtain FRD-TLEL model. QR probability different confidence intervals. experiments were conducted data at time level 15 min from Desert Knowledge Australia Solar Center (DKASC) forecast certain day. Compared other proposed lowest root mean square (RMSE) absolute percentage (MAPE) seasons types. In interval forecasting, 95%, 75%, 50% intervals all have good indicate that exhibits superior performance compared methods.

Language: Английский

---

Research on Photovoltaic Power Prediction Method Based on Dynamic Similar Selection and Bidirectional Gated Recurrent Unit

Advanced Theory and Simulations, Journal Year: 2025, Volume and Issue: unknown

Published: March 8, 2025

Abstract Photovoltaic (PV) power generation is vital for sustainable energy development, yet its inherent randomness and volatility challenge grid stability. Accurate short‐term PV prediction essential reliable operation. This paper proposes an integrated method combining dynamic similar selection (DSS), variational mode decomposition (VMD), bidirectional gated recurrent unit (BiGRU), improved sparrow search algorithm (ISSA). First, DSS selects training data based on local meteorological similarity, reducing interference. VMD then decomposes into smooth components, mitigating volatility. The Pearson correlation coefficient used to filter highly relevant variables, enhancing input quality. BiGRU captures temporal evolution patterns, with ISSA optimizing key parameters robust forecasting. Validated historical Australian under diverse weather conditions, the proposed effectively reduces volatility, significantly improving accuracy reliability. These advancements support stable supply efficient

Language: Английский

---

Prediction of Ultra-Short-Term Photovoltaic Power Using BiLSTM–Informer Based on Secondary Decomposition

Energies, Journal Year: 2025, Volume and Issue: 18(6), P. 1485 - 1485

Published: March 18, 2025

Photovoltaic power generation as a green energy source is often used in systems, but the volatility of PV output and randomness problem affect stability power-grid supply; so, for low prediction accuracy photovoltaic under different weather conditions, this paper proposes Variational Mode Decomposition (VMD), combined with Complementary Ensemble Empirical Adaptive Noise (CEEMDAN) secondary decomposition method original signal decomposition, to reduce complexity feature mapping data, followed by use BiLSTM model timing information decomposed IMF. Simultaneously, Informer predicts components obtained from finally, subsequence reconstructed superimposed obtain value. The results show that RMSE MAE proposed are improved up 10.91% 17.33% on annual dataset, high stability, which can effectively predict ultra-short-term plants.

Language: Английский

---