Optimized ensemble model for wind power forecasting using hybrid whale and dipper-throated optimization algorithms

Frontiers in Energy Research, Journal Year: 2023, Volume and Issue: 11

Published: June 21, 2023

Introduction: Power generated by the wind is a viable renewable energy option. Forecasting power generation particularly important for easing supply and demand imbalances in smart grid. However, biggest challenge with that it unpredictable due to its intermittent sporadic nature. The purpose of this research propose reliable ensemble model can predict future generation. Methods: proposed comprises three regression models: long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional LSTM models. To boost performance model, outputs each are optimally weighted form final prediction output. models’ weights optimized terms newly developed optimization algorithm based on whale dipper-throated algorithm. On other hand, converted binary be used feature selection results further. tested dataset publicly available Kaggle. Results discussion: compared six algorithms prove superiority In addition, statistical tests performed highlight approach’s effectiveness predicting values. evaluated using set criteria such as root mean square error (RMSE), absolute (MAE), R 2 . approach could achieve following results: RMSE = 0.0022, MAE 0.0003, 0.9999, which outperform those achieved methods.

Language: Английский

---

A Recommendation System for Electric Vehicles Users Based on Restricted Boltzmann Machine and WaterWheel Plant Algorithms

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 145111 - 145136

Published: Jan. 1, 2023

Ensuring reliable and easily accessible charging infrastructure becomes crucial as more people adopt electric vehicles. This study introduces a recommendation system designed to assist vehicle users in finding convenient stations, enhancing the experience, reducing range anxiety. The employs advanced data analysis techniques offer personalized suggestions based on users' preferences. Real-time factors like station availability, individual preferences, past usage patterns are collected processed using restricted Boltzmann machine-learning algorithm. waterwheel plant algorithm, known for its effectiveness solving complex optimization problems, is utilized optimize parameters of machine. considers various user including speed, cost, network compatibility, amenities, proximity user's current location. aims minimize frustration, improve performance, enhance customer satisfaction by addressing these aspects. Results indicate system's efficiency suggesting locations. explores statistical significance optimized algorithm machine model through Wilcoxon rank-sum Analysis Variance tests.

Language: Английский

---

“Advancements in Microstrip Patch Antenna Design Using Nature-Inspired Metaheuristic Optimization Algorithms: A Systematic Review”

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 29, 2025

Language: Английский

---

Machine learning assisted design of low-carbon aluminosilicate cementitious composites with diverse raw materials and target mechanical strength

Case Studies in Construction Materials, Journal Year: 2025, Volume and Issue: unknown, P. e04664 - e04664

Published: April 1, 2025

Language: Английский

---

Optimizing SVM hyperparameters for satellite imagery classification using metaheuristic and statistical techniques

International Journal of Data Science and Analytics, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Language: Английский

---