Enhancing photovoltaic parameter estimation: integration of non-linear hunting and reinforcement learning strategies with golden jackal optimizer

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 2, 2024

Abstract The advancement of Photovoltaic (PV) systems hinges on the precise optimization their parameters. Among numerous techniques, effectiveness each often rests inherent This research introduces a new methodology, Reinforcement Learning-based Golden Jackal Optimizer (RL-GJO). approach uniquely combines reinforcement learning with to enhance its efficiency and adaptability in handling various problems. Furthermore, incorporates an advanced non-linear hunting strategy optimize algorithm’s performance. proposed algorithm is first validated using 29 CEC2017 benchmark test functions five engineering-constrained design Secondly, rigorous testing PV parameter estimation datasets, including single-diode model, double-diode three-diode representative module, was carried out highlight superiority RL-GJO. results were compelling: root mean square error values achieved by RL-GJO markedly lower than those original other prevalent methods. synergy between GJO this facilitates faster convergence improved solution quality. integration not only improves performance metrics but also ensures more efficient process, especially complex scenarios. With average Freidman’s rank 1.564 for numerical engineering problems 1.742 problems, performing better peers. stands as reliable tool estimation. By seamlessly combining golden jackal optimizer, it sets optimization, indicating promising avenue future applications.

Language: Английский

---

Metaheuristic optimization algorithms for multi-area economic dispatch of power systems: part II—a comparative study

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(5)

Published: Feb. 14, 2025

Language: Английский

---

Marine Predators Algorithm: A Review

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(5), P. 3405 - 3435

Published: April 19, 2023

Language: Английский

---

LCAHA: A hybrid artificial hummingbird algorithm with multi-strategy for engineering applications

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2023, Volume and Issue: 415, P. 116238 - 116238

Published: July 23, 2023

Language: Английский

---

Enhancing parameter identification and state of charge estimation of Li-ion batteries in electric vehicles using an improved marine predators algorithm

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 84, P. 110982 - 110982

Published: Feb. 22, 2024

Language: Английский

---

A Novel Photovoltaic Power Prediction Method Based on a Long Short-Term Memory Network Optimized by an Improved Sparrow Search Algorithm

Electronics, Journal Year: 2024, Volume and Issue: 13(5), P. 993 - 993

Published: March 6, 2024

Photovoltaic (PV) power prediction plays a significant role in supporting the stable operation and resource scheduling of integrated energy systems. However, randomness volatility photovoltaic generation will greatly affect accuracy. Focusing on this issue, framework is proposed research by developing an improved sparrow search algorithm (ISSA) to optimize hyperparameters long short-term memory (LSTM) neural networks. The ISSA specially designed from following three aspects support powerful performance. Firstly, initial population variety enriched using enhanced sine chaotic mapping. Secondly, relative position neighboring producers introduced improve producer position-updating strategy enhance global capabilities. Then Cauchy–Gaussian variation utilized help avoid local optimal solution. Numerical experiments 20 test functions indicate that could identify solution with better precision compared SSA PSO algorithms. Furthermore, comparative study PV methods provided. ISSA-LSTM developed paper five benchmark models are implemented real dataset gathered Alice Springs area Australia. In contrast SSA-LSTM model, most MAE, MAPE, RMSE values model reduced 20∼60%, demonstrating superiority under various weather conditions typical seasons.

Language: Английский

---

Reinforcement learning guided auto-select optimization algorithm for feature selection

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 268, P. 126320 - 126320

Published: Jan. 5, 2025

Language: Английский

---

A quasi-oppositional learning of updating quantum state and Q-learning based on the dung beetle algorithm for global optimization

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 81, P. 469 - 488

Published: Sept. 22, 2023

There are many tricky optimization problems in real life, and metaheuristic algorithms the most effective way to solve at a lower cost. The dung beetle algorithm (DBO) is more innovative proposed 2022, which affected by action of beetles such as ball rolling, foraging, reproduction. Therefore, A based on quasi-oppositional learning Q-learning (QOLDBO). First, quantum state update idea cleverly integrated into increase randomness generated population. And best behavior pattern selected adding rolling stage improve search effect. In addition, variable spiral local domain method make up for shortage developing only around neighborhood optimum. For optimal solution each iteration, dimensional adaptive Gaussian variation retained. Experimental performance tests show that QOLDBO performs well both benchmark test functions CEC 2017. Simultaneously, validity verified several classical practical application engineering problems.

Language: Английский

---

An improved multi-strategy beluga whale optimization for global optimization problems

Mathematical Biosciences & Engineering, Journal Year: 2023, Volume and Issue: 20(7), P. 13267 - 13317

Published: Jan. 1, 2023

<abstract> <p>This paper presents an improved beluga whale optimization (IBWO) algorithm, which is mainly used to solve global problems and engineering problems. This improvement proposed the imbalance between exploration exploitation problem of insufficient convergence accuracy speed (BWO). In IBWO, we use a new group action strategy (GAS), replaces phase in BWO. It was inspired by hunting behavior whales nature. The GAS keeps individual belugas together, allowing them hide together from threat posed their natural enemy, tiger shark. also enables exchange location information enhance balance local lookups. On this basis, dynamic pinhole imaging (DPIS) quadratic interpolation (QIS) are added improve ability search rate IBWO maintain diversity. comparison experiment, performance algorithm tested using CEC2017 CEC2020 benchmark functions different dimensions. Performance analyzed observing experimental data, curves, box graphs, results were Wilcoxon rank sum test. show that has good robustness. Finally, applicability practical verified five problems.</p> </abstract>

Language: Английский

---

Humboldt Squid Optimization Algorithm (HSOA): A Novel Nature-Inspired Technique for Solving Optimization Problems

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 122069 - 122115

Published: Jan. 1, 2023

This study presents a new natural-based algorithm called the Humboldt Squid Optimization Algorithm (HSOA). HSOA is inspired by squids hunting, moving, and mating behavior. The search procedure involves an attack on fish schools, fish's escape, successful attack, of bigger smaller ones, mating, which inspiration for creating to address existing issues. In HSOA, half best populations are squid, rest school fish. Individuals connect with each other cooperate achieve optimal response. versatile applicable mathematical engineering problems. Solving eighty-four benchmark function problems (twenty-three classic functions, twenty-nine CEC-BC-2017 10, 30, 50, 100 dimensions, ten CEC-C06 2019, CEC2020 5, 15, 20 twelve CEC2022 10 dimensions) twenty-four (six CEC2006 eighteen CEC2011) shows that our proposed provides proper acceptable answers nine algorithms, including well-known (PSO, DE, WOA), recent (AVOA, RW_GWO, HHO GBO), state-of-the-art algorithms (LSHADE EBOwithCMAR). Friedman's rank from one hundred eight was 16.45% 7.45% lower than LSHADE EBOwithCMAR. Thus, has potential solve various complex in sciences fields.

Language: Английский

---