Non-linear robust identification of a greenhouse model using multi-objective evolutionary algorithms

Abstract

This paper presents the non-linear modelling, based on first principle equations, for a climatic (temperature & humidity) model of a greenhouse where roses are to be grown using hydroponic methods, and the fitting of its parameters (15 in all) based on real data collected for the summer period. To do so, a procedure for estimating a set of non-linear models Θ P (Pareto optimal) when several optimisation criteria are considered simultaneously within a multiobjective optimisation context is presented. A new multiobjective evolutionary algorithm, −M OGA, has been designed to converge towardsΘ * P , which is a reduced but well distributed representation of Θ P since good convergence and distribution of the Pareto front J(Θ P) is achieved by the algorithm. A posteriori,Θ * P can be used as the basis to choose an optimal model that offers a good relationship among the different optimality criteria that have been established, as has been shown by the results obtained in the identification and validation of the greenhouse model presented in this paper.

Optimizing the mixture of wood biomass for greenhouse heating

“…Linear programming (LP) model is a widely used methodology to solve optimization problems, such as biomass production planning, transportation scheduling, and financial decisionmaking [6][7][8]. Cundiff et al [9] formulated an LP model to minimize the transportation cost and the storage expansion cost from various on-farm storages to a fuel ethanol plant in the Piedmont of Virginia.…”

Modeling of Energy Demand in the Greenhouse Using PSO-GA Hybrid Algorithms

“…The evolutionary algorithms are model-based recognition methods and have been applied for uncertain optimization problems [11,12]. Some researchers have applied global optimization methods for calibration parameters in greenhouse microclimate model, such as genetic algorithm (GA), ant colony optimization (ACO), and particle swarm optimization (PSO) [13][14][15]. Hasni et al found that the performance of a greenhouse climate model using PSO is better than GA in terms of calculation time and accuracy of the results [16].…”

Hole distribution in phononic crystals: Design and optimization

“…This situation is usually known as a multi-objective problem and may be solved with an optimization algorithm called the multiobjective evolutionary algorithm. 30 In this work, we have used a new implementation of this tool based on genetic algorithms, termed the epsilon variable multi-objective genetic algorithm ͑evMOGA͒, 31,32 in conjunction with a multiple scattering theory ͑MST͒. 33 A parallel implementation of the evMOGA method is used here, and the execution time of the optimization process is drastically reduced.…”