Optimization of above-ground environmental factors in greenhouses using a multi-objective adaptive annealing genetic algorithm
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a multi-objective adaptive annealing genetic algorithm for optimizing greenhouse environments. The new algorithm significantly reduces energy consumption and infrastructure needs compared to traditional methods.
Area Of Science
- Agricultural Engineering
- Environmental Control Systems
- Computational Intelligence
Background
- Greenhouse environments are complex, nonlinear systems requiring multi-variable optimization.
- Existing methods struggle with dynamic conditions and extensive infrastructure for heating and humidity control.
Purpose Of The Study
- To develop and validate a multi-objective adaptive annealing genetic algorithm for optimizing greenhouse environmental factors.
- To address challenges in controlling temperature, relative humidity, and CO2 concentration efficiently.
Main Methods
- Developed a multi-objective, multi-constraint model for greenhouse environmental factors.
- Implemented a genetic algorithm with multi-parameter coding, a fitness function, and an annealing dynamic penalty factor.
- Validated the algorithm against traditional and single-objective genetic algorithms.
Main Results
- Achieved significant reductions in average temperature rise (20-34%) and humidification (2.39-3.9%).
- Reduced heating and humidification pipe lengths by up to 2.99 km and 0.443 km, respectively.
- Decreased required iterations by 170-240 times, saving 31-56% in running time.
Conclusions
- The multi-objective adaptive annealing genetic algorithm offers superior optimization for greenhouse environments.
- The algorithm enhances system stability, robustness, and energy efficiency.
- This approach provides a more effective solution for managing complex greenhouse conditions.

