Advanced Solar Irradiance Forecasting Using Hybrid Ensemble Deep Learning and Multisite Data Analytics for Optimal Solar‐Hydro Hybrid Power Plants

International Transactions on Electrical Energy Systems, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Solar energy with hydropower power plants marks a significant leap forward in renewable innovation. The combination ensures consistent supply by merging the fluctuations of solar predictable storage provided hydropower. This research aims to predict high irradiance on maximize active generation. A novel hybrid decomposed residual ensembling model for deep learning (SBL TSR R W) using models such as autoregressive integrated moving average (ARIMA) and seasonal‐trend decomposition loess (STL) along prediction optimization Bidirectional LSTM (Bi‐LSTM), Whale Optimization Algorithm (WOA) methods are used irradiances. Various forecasting methods, including STL‐Bi‐LSTM, SBL TS , T RS models, assessed determine their effectiveness predicting radiation. results show accuracy proposed model, RMSE MAE values 1.85 W/m 2 1.31 respectively. W more accurate than Bi‐LSTM, value reductions 517%, 217%, 151%, 98%, 1%,

Language: Английский

A Multi‐Strategy Fusion for Mobile Robot Path Planning via Dung Beetle Optimization

Concurrency and Computation Practice and Experience, Journal Year: 2025, Volume and Issue: 37(9-11)

Published: April 11, 2025

ABSTRACT In recent years, robot path planning has become a critical aspect of autonomous navigation, especially in dynamic and complex environments where robots must operate efficiently safely. One the primary challenges this domain is achieving high convergence efficiency while avoiding local optimal solutions, which can hinder robot's ability to find best possible path. Additionally, ensuring that follows with minimal turns reduced length essential for enhancing operational reducing energy consumption. These even more pronounced high‐dimensional optimization tasks search space vast difficult navigate. article, multi‐strategy fusion enhanced dung beetle algorithm (MIDBO) introduced tackle key planning, such as slow problem optima, so on, MIDBO incorporates several innovations enhance performance robustness. First, Tent chaotic strategy used diversify initial solutions during population initialization, thereby mitigating risk optima improving global capability. Second, penalty term integrated into fitness function penalize excessive turning angles, aiming reduce frequency magnitude turns. This modification results smoother efficient paths lengths. Third, inertia weight adaptively updated by sine‐based mechanism, dynamically balances exploration exploitation, accelerates convergence, enhances stability. To further improve integrates Levy flight mechanism boost capability stealing phase, contributing practical planned robot. A series thorough reproducible experiments are performed using benchmark test functions evaluate comparison leading metaheuristic algorithms. The demonstrate achieves superior outcomes mean lengths 42.1068 44.4755, respectively, significantly outperforms other algorithms including IPSO (47.6244, 55.9375), original DBO ISSA 55.9375). also markedly reduces number average values 10 13.4, compared (11, 16.1), (12, 15.3), 16.4). Besides, consistent confirmed via stability analysis based on square error turn counts across independent trials. For tasks, 8 7 about top rankings 50‐ 100‐dimensional functions, specifically DBO, IPSO, 13, 18, 11 respectively. Therefore, findings validate competitive solution mobile navigation requirements.

Language: Английский

Hybrid path planning algorithm for robots based on modified golden jackal optimization method and dynamic window method

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127808 - 127808

Published: April 1, 2025

Language: Английский