A combined improved dung beetle optimization and extreme learning machine framework for precise SOC estimation

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 20, 2025

Accurate estimation of the state charge (SOC) lithium-ion batteries (LiBs) proportionally impacts efficiency battery management systems (BMS) considering dynamic and non-linear behavior LiBs. Changes in activities cathode anode materials internal resistance tend to impact capacity. When is operated at high or low temperatures under HWFET condition, capacity tends deteriorate drastically. Therefore, high-precision SOC required ensure safe stable operation. In this work, we propose a combined Improved Dung Beetle Optimization (IDBO) Extreme Learning Machine (ELM) framework for evaluate BMS. The novelty model stems from application IDBO algorithm, which incorporating Circle chaotic mapping, Golden sine strategy, Levy flight hyper-parameter optimization. This effectively resolves problems inconsistent performance instability arising randomly initialized hidden layer weights biases ELM, resulting enhanced prediction accuracy. proposed IDBO-ELM method validated context five parameters, namely, different ambient temperatures, operating conditions, materials, initial values, running time. experimental results show that error ranges both MAE RMSE conditions are around 1.4%, demonstrating precision robustness. decreased by more than 30%, respectively, compared those DBO-ELM. provides strong support efficient LiBs various practical conditions.

Язык: Английский

---

IGWO-VINC Algorithm Applied to MPPT Strategy for PV System

International Journal of Photoenergy, Год журнала: 2024, Номер 2024, С. 1 - 16

Опубликована: Май 27, 2024

As a kind of inexhaustible renewable energy, solar energy is popular, and photovoltaic power generation has been paid attention to by all circles. However, determining the global maximum point (GMPP) difficult under external ambient temperature light intensity change, MPPT control technology becomes key research. Fast, accurate, stable GMPP capture become hot research problem in PV systems. The GWO algorithm incorporating Levy flight function INC using vertex as dividing with different step sizes on left right sides are combined applied strategy search completed IGWO first, then exact improved when it close optimum. final tracking accuracy above 99%, compared GWO, INC, ICS-IP&O algorithms, respectively, case abrupt changes, time accelerated 0.021 s average. oscillation amplitude smaller, voltage more stable.

Язык: Английский

---

Improving maximum power point tracking efficiency in solar photovoltaic systems using super‐twisting algorithm and grey wolf optimizer

IET Renewable Power Generation, Год журнала: 2024, Номер 18(15), С. 3329 - 3354

Опубликована: Окт. 19, 2024

Abstract This study presents a new Maximum Power Point Tracking (MPPT) approach for solar photovoltaic (PV) systems, combining the Super‐Twisting Algorithm (STA) and Grey Wolf Optimizer (GWO). The STA‐GWO‐MPPT method improves efficiency in dynamic conditions by using STA control GWO parameter optimization, enhancing stability robustness. Performance evaluation is conducted through MATLAB/Simulink simulations experimental validation on small‐scale test bench. Various quantitative metrics, including rise time, settling power production, efficiency, root mean square error (RMSE), standard deviation (STD), are employed assessment. Results indicate significantly faster convergence speeds proposed compared to conventional MPPT techniques. Specifically, time 0.0129 seconds, outperforming Fuzzy Logic Control (FLC) (0.2638 seconds) with Sliding Mode (GWO‐SMC) (0.0181 seconds). Additionally, exhibits superior tracking an average of 99.33%, surpassing FLC (96.93%) GWO‐SMC (99.19%). Moreover, it reduces fluctuations, RMSE 7.819% STD 6.547%, (RMSE: 13.471%, STD: 4.519%) 8.507%, 6.108%). Overall, this contributes valuable insights into PV implications both research practical applications.

Язык: Английский

---

Improving photovoltaic energy harvesting systems with hybrid fuzzy logic-PI MPPT optimized by PSO under normal and partial shading conditions

Electrical Engineering, Год журнала: 2024, Номер unknown

Опубликована: Окт. 22, 2024

Язык: Английский

---

Optimizing makespan and resource utilization in cloud computing environment via evolutionary scheduling approach

PLoS ONE, Год журнала: 2024, Номер 19(11), С. e0311814 - e0311814

Опубликована: Ноя. 22, 2024

As a new computing resources distribution platform, cloud technology greatly influenced society with the conception of on-demand resource usage through virtualization technology. Virtualization allows physical in way that will enable multiple end-users to have similar hardware infrastructure. In cloud, many challenges exist on provider side due expectations clients. Resource scheduling (RS) is most significant nondeterministic polynomial time (NP) hard problem owing its crucial impact performance. Previous research found metaheuristics can dramatically increase CC performance if deployed as algorithms. Therefore, this study develops an evolutionary algorithm-based approach for makespan optimization and utilization (EASA-MORU) technique environment. The EASA-MORU aims maximize effectively use technique, dung beetle (DBO) used purposes. Moreover, balances load properly distributes based demands evaluation method tested using series measures. A wide range comprehensive comparison studies emphasized performs better than other methods different

Язык: Английский

---

Enhanced power quality and efficient photovoltaic integration with a PV-based unified power quality conditioner using optimized MPPT technique

Electrical Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июль 25, 2024

Язык: Английский

---

Multisource Modeling Method for Petroleum Production Prediction Models: A Case Study of CO2-Flooding Performance

SPE Journal, Год журнала: 2024, Номер unknown, С. 1 - 18

Опубликована: Сен. 1, 2024

Summary Accurate prediction of oil production is crucial for formulating oilfield development strategies. With the rapid artificial intelligence, research on utilizing deep learning to construct models has been growing, which partially compensated low computational efficiency numerical simulators. Although well-trained source domain model maintains high accuracy target blocks with similar conditions, declines in scenarios where substantial disparities exist between conditions block and domain. This discrepancy makes results unreliable causes a shift issue. We propose multisource fine-tuning approach, leverages limited amount data fine-tune existing model, enabling it rapidly converge while maintaining superior performance. Based heterogeneous low-permeability CO2-flooding reservoir we established series sets, encompassing numerous types well patterns permeability fields, specifically prepared various sets verify effectiveness fine-tuning. Experimental outcomes demonstrate that our proposed approach facilitates convergence data. Following testing, fine-tuned attained exceeding 97% domain, significantly improved upon compared unfine-tuned model. The time required lower than retraining new reduces need provides support generation using

Язык: Английский

---

Path Planning for Yarn Changing Robots Based on NRBO and Dynamic Obstacle Avoidance Strategy

Applied Sciences, Год журнала: 2024, Номер 14(23), С. 11086 - 11086

Опубликована: Ноя. 28, 2024

To address the shortcomings of traditional bionic algorithms in path planning, such as inefficient search processes, extended planning distances and times, suboptimal dynamic obstacle avoidance, this paper introduces a fusion algorithm called NRBO-DWA. This is specifically applied to plan for tube-changing robot knitting workshop. The process begins with spatial modeling based on actual parameters workshop, followed by development comprehensive, objective function line relevant constraints. NRBO then integrated DWA boost its avoidance capabilities, while correction mechanism introduced minimize unnecessary detours. Finally, comparative experiment designed evaluate against GA, PSO, SSA algorithms. Simulation results demonstrate that dynamically complex 3D environment, NRBO-DWA outperforms terms higher efficiency, shorter total length, faster times.

Язык: Английский

---

An efficient photovoltaic system with strong control capabilities that significantly increases performance under complex real-world PV meteorological conditions

Renewable Energy, Год журнала: 2024, Номер unknown, С. 122241 - 122241

Опубликована: Дек. 1, 2024

Язык: Английский

---