Performance Comparison of Bio-Inspired Algorithms for Optimizing an ANN-Based MPPT Forecast for PV Systems

Biomimetics, Journal Year: 2024, Volume and Issue: 9(10), P. 649 - 649

Published: Oct. 21, 2024

This study compares bio-inspired optimization algorithms for enhancing an ANN-based Maximum Power Point Tracking (MPPT) forecast system under partial shading conditions in photovoltaic systems. Four algorithms—grey wolf optimizer (GWO), particle swarm (PSO), squirrel search algorithm (SSA), and cuckoo (CS)—were evaluated, with the dataset augmented by perturbations to simulate shading. The standard ANN performed poorly, 64 neurons Layer 1 32 2 (MSE of 159.9437, MAE 8.0781). Among optimized approaches, GWO, 66 100 2, achieved best prediction accuracy 11.9487, 2.4552) was computationally efficient (execution time 1198.99 s). PSO, using 98 minimized (2.1679) but had a slightly longer execution (1417.80 SSA, same neuron count as also well 12.1500, 2.7003) fastest (987.45 CS, 84 74 less reliable 33.7767, 3.8547) slower (1904.01 GWO proved be overall, balancing speed. Future real-world applications this methodology include improving energy efficiency solar farms variable weather optimizing performance residential panels reduce costs. Further developments could address more complex larger-scale datasets real-time, such integrating renewable sources into smart grid systems better distribution.

Language: Английский

---

Development and Experiment of Semi-Physical Simulation Platform for Space Manipulator

Sensors, Journal Year: 2024, Volume and Issue: 24(13), P. 4354 - 4354

Published: July 4, 2024

To address the extended development cycle, high costs, and maintenance difficulties associated with existing microgravity simulation methods, this study has developed a semi-physical platform for robotic arms tailored to different gravity environments loading conditions. The represents difficult-to-model joints as physical objects, while easily modeled components are simulated based on principles of similarity. In response strong coupling, nonlinearity, excess force disturbance issues in electric variable load system, fractional-order linear active rejection control algorithm was employed. controller parameters were tuned using an improved particle swarm modified weight coefficients, experimental results demonstrate that improves speed performance compared sliding mode control. investigated differences drive joint motors space under varying Experimental indicate torque is primary influencing factor motor force, radial serves secondary factor. Additionally, when axis perpendicular ground, it can, some extent, simulate conditions ground.

Language: Английский

---

Control of Thermal Uniformity in Microwave Heating Process by BPNN and Adaptive Particle Swarm Optimization

Heliyon, Journal Year: 2024, Volume and Issue: 10(21), P. e37971 - e37971

Published: Sept. 14, 2024

As China advances its green economy, innovative methods are being employed to enhance energy optimization and conservation within energy-intensive industries. Among these methods, microwave heating stands out due superior efficiency lack of pollution. Nonetheless, uniform remains a challenge because the absorption capacity heated medium varies with changes in time temperature. To address this issue, an Adaptive Particle Swarm Optimization (APSO) neural network system based on Back Propagation Neural Network (BPNN) is proposed. This leverages fundamental principles (PSO), categorizing particle swarms into three types iterating them through distinct processes achieve optimal results. An APSO controller designed identification, adjusting parameters according error between real-time output identification model. The feedback used as fitness function PSO algorithm, continuously weights thresholds network. intelligent control approach optimizes oven's input power minimize actual temperature identified intelligently controlled outputs. Unlike traditional Proportional Integral Differential (PID) BPNN controllers, calculates model model, feeding information back controller. serves enabling continuous adjustment network's regulate equipment's power, thereby ensuring closely follows preset curve. Experimental results demonstrate that value aligns original curve, root mean square only 0.74. effectively achieves desired outcome.

Language: Английский

---

Dual-objective economic planning of simultaneous allocation of disconnectors and maneuvering points considering the direction of error reduction in the presence of fault detector with the multi-objective PSO

Electrical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 25, 2024

Language: Английский

---