ABSTRACT
Optimal control of greenhouse environments can be improved by using a combined microclimate-crop-yield model to allow selection of greenhouse designs and control algorithms to maximize the profit margin. However, classical methods for optimal greenhouse control are not adequate to establish the tradeoffs between multiple objectives. We use NSGA-II to evolve the setpoints for microclimate control in a greenhouse simulation and define two objectives: minimizing variable costs and maximizing the value of the tomato crop yield. Results show that the evolved setpoints can provide the grower a variety of better solutions, resulting in greater profitability compared to prior simulated results. The Pareto front also provides additional information to the grower, showing the economic tradeoffs between variable costs and tomato crop yield, which can aid in decision making.
- Deb, K., Pratap, A., Agarwal, S. and Meyarivan, T. A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6, 2 (2002), 182--197. Google ScholarDigital Library
- Vanthoor, B. H. A Model-Based Greenhouse Design Method. PhD. Dissertation. Wageningen University, Wageningen, The Netherlands. 2011.Google Scholar
- Xu, L., Hu, H. and Zhu, B. Energy-saving control of greenhouse climate based on MOCC strategy. In Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC 09) ACM, New York, NY, USA, 645--650. Google ScholarDigital Library
- Zhu, C., Unachak, P., Llera, J., Knoester, D., Runkle, E., Xu, L. and Goodman, E. Robust multi-objective evolutionary optimization to allow greenhouse production/energy use tradeoffs. Acta horticulturae (2014). International Society for Horticultural Science, 1037, (2014), 525--532. Leuven, Belgium, 2014.Google Scholar
Index Terms
- Improving greenhouse environmental control using crop-model-driven multi-objective optimization
Recommendations
Sensor placement determination for range-difference positioning using evolutionary multi-objective optimization
Sensor placement according to different performance measures obtained from the CRLB.The proposed approach is valid for different positioning technologies.Simulations are performed for an infrared positioning system used as example.The examples obtain ...
Multi-objective evolutionary optimization based on online perceiving Pareto front characteristics
AbstractWhen solving multi-objective optimization problems with complex Pareto fronts characteristics, previous work generally ignores the information related to Pareto fronts provided by the population during the evolution, which is ...
Multi-objective optimization using teaching-learning-based optimization algorithm
Two major goals in multi-objective optimization are to obtain a set of nondominated solutions as closely as possible to the true Pareto front (PF) and maintain a well-distributed solution set along the Pareto front. In this paper, we propose a teaching-...
Comments