Evolution and Evolutionary Algorithms

Camara, Daniel

doi:10.1016/b978-1-78548-021-8.50001-6

Cited by 12 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic steps of the GA include initialization, evaluation and reproduction (selection, crossover, mutation) (Holland, 1975;Câmara, 2015;Yang et al, 2015). The initialization step generates an initial population whose size can be changed from a few individuals to thousands.…”

Section: Fractional Order Calculus and Controllersmentioning

confidence: 99%

PSO and GA tuned conventional and fractional order PID controllers for quadrotor control

Sarıbaş

Kahvecioglu

2021

AEAT

View full text Add to dashboard Cite

Purpose This study aims to compare the performance of the conventional and fractional order proportional-integral-derivative (PID and FOPID) controllers tuned with a particle swarm optimization (PSO) and genetic algorithm (GA) for quadrotor control. Design/methodology/approach In this study, the gains of the controllers were tuned using PSO and GA, which are included in the heuristic optimization methods. The tuning processes of the controller’s gains were formulated as optimization problems. While generating the objective functions (cost functions), four different decision criteria were considered separately: integrated summation error (ISE), integrated absolute error, integrated time absolute error and integrated time summation error (ITSE). Findings According to the simulation results and comparison tables that were created, FOPID controllers tuned with PSO performed better performances than PID controllers. In addition, the ITSE criterion returned better results in control of all axes except for altitude control when compared to the other cost functions. In the control of altitude with the PID controller, the ISE criterion showed better performance. Originality/value While a conventional PID controller has three parameters (Kp, Ki, Kd) that need to be tuned, FOPID controllers have two additional parameters (µ). The inclusion of these two extra parameters means more flexibility in the controller design but much more complexity for parameter tuning. This study reveals the potential and effectiveness of PSO and GA in tuning the controller despite the increased number of parameters and complexity.

show abstract

Section: Fractional Order Calculus and Controllersmentioning

confidence: 99%

PSO and GA tuned conventional and fractional order PID controllers for quadrotor control

Sarıbaş

Kahvecioglu

2021

AEAT

View full text Add to dashboard Cite

show abstract

“…To allow Theseus EVO to respond to its environment, we employed the setting of an evolutionary (genetic) algorithm (EA or GA), i.e. a computerized optimization process modelled on the mechanisms of natural selection [35][36][37]. Fundamentally, an EA optimization procedure is based on the principle of encoding the parameters of a fitness function (the optimization problem) in such a way that they behave Theseus cyber genetics (bottom) has a double set of chromosomes that carry the rules represented as alleles.…”

Section: Theseus Cyber Spider Web Building and Web Evolutionmentioning

confidence: 99%

Spider webs inspiring soft robotics

Vollrath

Krink

2020

J. R. Soc. Interface.

View full text Add to dashboard Cite

In soft robotics, bio-inspiration ranges from hard- to software. Orb web spiders provide excellent examples for both. Adapted sensors on their legs may use morphological computing to fine-tune feedback loops that supervise the handling and accurate placement of silk threads. The spider's webs embody the decision rules of a complex behaviour that relies on navigation and piloting laid down in silk by behaviour charting inherited rules. Analytical studies of real spiders allow the modelling of path-finding construction rules optimized in evolutionary algorithms. We propose that deconstructing spiders and unravelling webs may lead to adaptable robots able to invent and construct complex novel structures using relatively simple rules of thumb.

show abstract

“…Thanks to advancements in computational resources, better technologies and more robust equipment, metaheuristic techniques have been gaining popularity in the field of water resources. Such is the case for evolutionary algorithms (EA) that use the mechanisms of Darwin's evolution of species (see Cámara, 2015;Loucks & van Beek, 2017). When applied to multi-objective optimization, EAs are efficient because of their ability to solve complex problems involving characteristics such as discontinuities, multi-modality, disjoint feasible spaces and noise when evaluating functions (Ma et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization of Reservoir Operation using Machine Learning Models. Case study: Hatillo Reservoir in the Dominican Republic

Tami

Corzo

Franco

et al. 2022

Preprint

View full text Add to dashboard Cite

Finding optimum balances between conflicting interests in multipurpose reservoirs often represents an important challenge for decision makers. This study assesses the use of different computational tools to obtain optimal reservoir operations applied to the Hatillo dam in the Dominican Republic. A multiobjective optimization approach is used, in which non-dominated sorting genetic algorithm II (NSGAII) and multi-objective evolutionary algorithm based on decomposition (MOEA/D) optimizers are applied to models that simulate reservoir operations. Three different Machine Learning (ML) models, namely, the multilayer perceptron (MLP), the radial basis network (RBN) and the linear function (LF), are employed to learn the current operation of the system. Subsequently, a general model is proposed to simulate daily reservoir operations (2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018)(2019), integrating water balances, physical constraints of the dam components and the ML models, the latter defining daily controlled discharges. In the optimization process, the ML parameters are the decision variables, while the objectives evaluated are irrigation, hydropower generation and flood control. The results are compared with the actual operation of the reservoir. Three dimensional Pareto fronts are obtained, from which, the wide variety of operations can be evidenced. The flood control objective was found to have a wide room for improvement over the current operation of the reservoir, and several of the solutions found improve the current operation for the three proposed objectives. The MLP models tend to generate the best results for this case study and the NSGAII optimizer generates the best optimization results.

show abstract

Evolution and Evolutionary Algorithms

Cited by 12 publications

References 23 publications

PSO and GA tuned conventional and fractional order PID controllers for quadrotor control

PSO and GA tuned conventional and fractional order PID controllers for quadrotor control

Spider webs inspiring soft robotics

Multi-Objective Optimization of Reservoir Operation using Machine Learning Models. Case study: Hatillo Reservoir in the Dominican Republic

Contact Info

Product

Resources

About