Evolutionary algorithms have proved to be useful for tackling many practical black-box optimization problems. In this thesis, we describe one of the most powerful evolutionary algorithms of today, CMA- ES, and apply it in novel way to solve the problem of tuning multiple coupled PID controllers in combustion engine models. Powered by TCPDF (www.tcpdf.org)

This thesis introduces a new optimization algorithm for simulation-based design of systems with multi-modal, nonlinear, black box objective functions. The algorithm extends the recently introduced adaptive multi-modal optimization by incorporating surrogate modeling features similar to response surface methods (RSM). The resulting optimization algorithm has reduced computational intensity and is therefore well-suited for optimization of expensive black box objective functions. The algorithm relies on an adaptive and multi-resolution mesh to obtain an initial estimation of the objective function surface. Local surrogate models are then constructed to represent the objective function and to generate additional trial points in the vicinity of local minima discovered. The steps of mesh refinement and surrogate modeling continue until convergence criteria are met. An important property of this algorithm is that it produces progressively accurate surrogate models around the local minima; these models can be used for post-optimization studies such as sensitivity and tolerance analyses with minimal computational effort. This algorithm is suitable for optimal design of complex engineering systems and enhances the design cycle by enabling computationally affordable uncertainty analysis. The mathematical basis of the algorithm is explained in detail. The thesis also demonstrates the effectiveness of the algorithm using comparative optimization of several multi-modal objective functions. It also shows several practical applications of the algorithm in the design of complex power and power-electronic systems.

This thesis introduces a new optimization algorithm for simulation-based design of systems with multi-modal, nonlinear, black box objective functions. The algorithm extends the recently introduced adaptive multi-modal optimization by incorporating surrogate modeling features similar to response surface methods (RSM). The resulting optimization algorithm has reduced computational intensity and is therefore well-suited for optimization of expensive black box objective functions. The algorithm relies on an adaptive and multi-resolution mesh to obtain an initial estimation of the objective function surface. Local surrogate models are then constructed to represent the objective function and to generate additional trial points in the vicinity of local minima discovered. The steps of mesh refinement and surrogate modeling continue until convergence criteria are met. An important property of this algorithm is that it produces progressively accurate surrogate models around the local minima; these models can be used for post-optimization studies such as sensitivity and tolerance analyses with minimal computational effort. This algorithm is suitable for optimal design of complex engineering systems and enhances the design cycle by enabling computationally affordable uncertainty analysis. The mathematical basis of the algorithm is explained in detail. The thesis also demonstrates the effectiveness of the algorithm using comparative optimization of several multi-modal objective functions. It also shows several practical applications of the algorithm in the design of complex power and power-electronic systems.

In this thesis, the theory and application of black-box optimization methods are explored. More specifically, we looked at two families of algorithms, descent methods andresponse surface methods (closely related to trust region methods). We also looked at possibilities in using a dimension reduction technique called active subspace which utilizes sampled gradients. This dimension reduction technique can make the descent methods more suitable to high-dimensional problems, which turned out to be most effective when the data have a ridge-like structure. Finally, the optimization methods were used on a real-world problem in the context of pre-hospital care where the objective is to minimize the ambulance response times in the municipality of Umea by changing the positions of the ambulances. Before applying the methods on the real-world ambulance problem, a simulation study was performed on synthetic data, aiming at finding the strengths and weaknesses of the different models when applied to different test functions, at different levels of noise. The results showed that we could improve the ambulance response times across several different performance metrics compared to the response times of the current ambulancepositions. This indicates that there exist adjustments that can benefit the pre-hospitalcare in the municipality of Umea. However, since the models in this thesis work find local and not global optimums, there might still exist even better ambulance positions that can improve the response time further. / I denna rapport undersöks teorin och tillämpningarna av diverse blackbox optimeringsmetoder. Mer specifikt så har vi tittat på två familjer av algoritmer, descentmetoder och responsytmetoder (nära besläktade med tillitsregionmetoder). Vi tittar också på möjligheterna att använda en dimensionreduktionsteknik som kallas active subspace som använder samplade gradienter för att göra descentmetoderna mer lämpade för högdimensionella problem, vilket visade sig vara mest effektivt när datat har en struktur där ändringar i endast en riktning har effekt på responsvärdet. Slutligen användes optimeringsmetoderna på ett verkligt problem från sjukhusvården, där målet var att minimera svarstiderna för ambulansutryckningar i Umeå kommun genom att ändra ambulanspositionerna. Innan metoderna tillämpades på det verkliga ambulansproblemet genomfördes också en simuleringsstudie på syntetiskt data. Detta för att hitta styrkorna och svagheterna hos de olika modellerna genom att undersöka hur dem hanterar ett flertal testfunktioner under olika nivåer av brus. Resultaten visade att vi kunde förbättra ambulansernas responstider över flera olika prestandamått jämfört med responstiderna för de nuvarande ambulanspositionerna. Detta indikerar att det finns förändringar av positioneringen av ambulanser som kan gynna den pre-hospitala vården inom Umeå kommun. Dock, eftersom modellerna i denna rapport hittar lokala och inte globala optimala punkter kan det fortfarande finnas ännu bättre ambulanspositioner som kan förbättra responstiden ytterligare.

The simulation program GTperform is used to estimate the machine settings from performance measurements for the gas turbine model STG-800 at Siemens Industrial Turbomachinery in Finspång, Sweden. By evaluating different settings within the program, the engineers try to estimate the one that generatesthe performance measurement. This procedure is done manually at Siemens and is very time-consuming. This project aims to establish an algorithm that automatically establishes the correct machine setting from the performance measurements. Two algorithms were implemented in Python: Simulated Annealing and Gradient Descent. The algorithms analyzed two possible objective functions, and objective were tested on three gas turbines located at different locations. The first estimated the machine setting that generated the best fit to the performance measurements, while the second established the most likely solution for the machine setting from probability distributions. Multiple simulations have been run for the two algorithms and objective functions to evaluate the performances. Both algorithms successfully established satisfactory results for the second objective function. The Simulated Annealing, in particular, established solutions with a lower spread compared to Gradient Descent. The algorithms give a possibility to automatically establish the machine settings for the simulation program, reducing the work for the engineers.

Designing products and processes is a fundamental aspect of engineering that significantly impacts society and the world. Chemical process design aims to create more efficient and sustainable production processes that consume fewer resources and emit less pollution. Mathematical models that accurately describe process behavior are necessary to make informed and responsible decisions. However, as processes become more complex, purely symbolic formulations may be inadequate, and simulations using tailored computer code become necessary. The decision‐making process in optimal design requires a procedure for choosing the best option while complying with the system’s constraints, for which task optimization approaches are well suited. This doctoral thesis focuses on black‐box optimization problems that arise when using process simulators in optimal process design tasks and assesses the potential of derivative‐free, metaheuristics, and surrogate‐based optimization approaches. The optimal design of natural gas liquefaction processes is the case study of this research. To overcome numerical issues from black‐box problems, the first work of this doctoral thesis consisted of using the globally convergent Nelder‐Mead simplex method to the optimal process design problem. The second work introduced surrogate models to assist the search towards the global optimum of the black‐box problem and an adaptive sampling scheme comprising the optimization of an acquisition function with metaheuristics. Kriging as surrogate models to the simulation‐optimization problems are computationally cheaper and effective predictors suitable for global search. The third work aims to overcome the limitations of acquisition function optimization and the use of metaheuristics. The proposed comprehensive mathematical notation of the surrogate optimization problem was readily implementable in algebraic modeling language software. The presented framework includes kriging models of the objective and constraint functions, an adaptive sampling procedure, a heuristic for stopping criteria, and a readily solvable surrogate optimization problem with mathematical programming. The success of the surrogate‐based optimization framework relies on the kriging models’ prediction accuracy regarding the underlying, simulation‐based functions. The fourth publication extends the previous work to multi‐objective black‐box optimization problems. It applies the ε constraint method to transform the multi‐objective surrogate optimization problem into a sequence of single‐objective ones. The ε‐constrained surrogate optimization problems are implemented automatically in algebraic modeling language software and solved using a gradient‐based, state‐of‐the‐art solver. The fifth publication is application-driven and focuses on identifying the most suitable mixed‐refrigerant refrigeration technology for natural gas liquefaction in terms of energy consumption and costs. The study investigates five natural gas liquefaction processes using particle swarm optimization and concludes that there are flaws in the expected relationships between process complexity, energy consumption, and total annualized costs. In conclusion, the research conducted in this doctoral thesis demonstrates the importance and capabilities of using optimization to process simulators. The work presented here highlights the potential of surrogate‐based optimization approaches to significantly reduce the computational cost and guide the search in black‐box optimization problems with chemical process simulators embedded. Overall, this doctoral thesis contributes to developing optimization strategies for complex chemical processes that are essential for addressing some of the current most pressing environmental and social challenges. The methods and insights presented in this work can help engineers and scientists design more sustainable and efficient processes, contributing to a better future for all.

This thesis fits into the Multiple-Input Multiple-Output (MIMO) communication systems. Nowadays, these schemes are the most promising technology in the field of wireless communications. The use of this technology allows to increase the rate and the quality of the transmission through the use of multiple antennas at the transmitter and receiver sides. Furthermore, the MIMO technology can also be used in a multiuser scenario, where a Base Station (BS) equipped with several antennas serves several users that share the spatial dimension causing interference. However, employing precoding algorithms the signal of the multiuser interference can be mitigated. For these reasons, the MIMO technology has become an essential key in many new generation communications standards. On the other hand, Massive MIMO technology or Large MIMO, where the BS is equipped with very large number of antennas (hundreds or thousands) serves many users in the same time-frequency resource. Nevertheless, the advantages provided by the MIMO technology entail a substantial increase in the computational cost. Therefore the design of low-complexity receivers is an important issue which is tackled throughout this thesis. To this end, one of the main contributions of this dissertation is the implementation of efficient soft-output detectors and precoding schemes. First, the problem of efficient soft detection with no iteration at the receiver has been addressed. A detailed overview of the most employed soft detectors is provided. Furthermore, the complexity and performance of these methods are evaluated and compared. Additionally, two low-complexity algorithms have been proposed. The first algorithm is based on the efficient Box Optimization Hard Detector (BOHD) algorithm and provides a low-complexity implementation achieving a suitable performance. The second algorithm tries to reduce the computational cost of the Subspace Marginalization with Interference Suppression (SUMIS) algorithm. Second, soft-input soft-output (SISO) detectors, which are included in an iterative receiver structure, have been investigated. An iterative receiver improves the performance with respect to no iteration, achieving a performance close to the channel capacity. In contrast, its computational cost becomes prohibitive. In this context, three algorithms are presented. Two of them achieve max-log performance reducing the complexity of standard SISO detectors. The last one achieves near max-log performance with low complexity. The precoding problem has been addressed in the third part of this thesis. An analysis of some of the most employed precoding techniques has been carried out. The algorithms have been compared in terms of performance and complexity. In this context, the impact of the channel matrix condition number on the performance of the precoders has been analyzed. This impact has been exploited to propose an hybrid precoding scheme that reduces the complexity of the previously proposed precoders. In addition, in Large MIMO systems, an alternative precoder scheme is proposed. In the last part of the thesis, parallel implementations of the SUMIS algorithm are presented. Several strategies for the parallelization of the algorithm are proposed and evaluated on two different platforms: multicore central processing unit (CPU) and graphics processing unit (GPU). The parallel implementations achieve a significant speedup compared to the CPU version. Therefore, these implementations allow to simulate a scalable quasi optimal soft detector in a Large MIMO system much faster than by conventional simu / La presente tesis se enmarca dentro de los sistemas de comunicaciones de múltiples antenas o sistemas MIMO. Hoy en día, estos sistemas presentan una de las tecnologías más prometedoras dentro de los sistemas comunicaciones inalámbricas. A través del uso de múltiples antenas en ambos lados, transmisor y receptor, la tasa de transmisión y la calidad de la misma es aumentada. Por otro lado, la tecnología MIMO puede ser utilizada en un escenario multiusuario, donde una estación base (BS) la cual está equipada con varias antenas, sirve a varios usuarios al mismo tiempo, estos usuarios comparten dimensión espacial causando interferencias multiusuario. Por todas estas razones, la tecnología MIMO ha sido adoptada en muchos de los estándares de comunicaciones de nueva generación. Por otro lado, la tecnología MIMO Masivo, en la cual la estación base está equipada con un gran número de antenas (cientos o miles) que sirve a muchos usuarios en el mismo recurso de tiempo-frecuencia. Sin embargo, las ventajas proporcionadas por los sistemas MIMO implican un aumento en el coste computacional requerido. Por ello, el diseño de receptores de baja complejidad es una cuestión importante en estos sistemas. Para conseguir esta finalidad, las principales contribuciones de la tesis se basan en la implementación de algoritmos de detección soft y esquemas de precodificación eficientes. En primer lugar, el problema de la detección soft eficiente en un sistema receptor sin iteración es abordado. Una descripción detallada sobre los detectores soft más empleados es presentada. Por otro lado, han sido propuestos dos algoritmos de bajo coste. El primer algoritmo está basado en el algoritmo Box Optimization Hard Detector (BOHD) y proporciona una baja complejidad de implementación logrando un buen rendimiento. El segundo de los algoritmos propuestos intenta reducir el coste computacional del conocido algoritmo Subspace Marginalization with Interference Suppression (SUMIS). En segundo lugar, han sido investidados detectores de entrada y salida soft (SISO, soft-input soft-output) los cuales son ejecutados en estructuras de recepción iterativa. El empleo de un receptor iterativo mejora el rendimiento del sistema con respecto a no realizar realimentación, pudiendo lograr la capacidad óptima. Por el contrario, el coste computacional se vuelve prohibitivo. En este contexto, tres algoritmos han sido presentados. Dos de ellos logran un rendimiento óptimo, reduciendo la complejidad de los detectores SISO óptimos que normalmente son empleados. Por el contrario, el otro algoritmo logra un rendimiento casi óptimo a baja complejidad. En la tercera parte, se ha abordado el problema de la precodificación. Se ha llevado a cabo un análisis de algunas de las técnicas de precodificación más usadas. En este contexto, se ha evaluado el impacto que el número de condición de la matriz de canal tiene en el rendimiento de los precodificadores. Además, se ha aprovechado este impacto para proponer un precodificador hibrido. Por otro lado, en MIMO Masivo, se ha propuesto un esquema precodificador. En la última parte de la tesis, la implementación paralela del algoritmo SUMIS es presentada. Varias estrategias sobre la paralelización del algoritmo han sido propuestas y evaluadas en dos plataformas diferentes: Unidad Central de Procesamiento multicore (multicore CPU) y Unidad de Procesamiento Gráfico (GPU). Las implementaciones paralelas consiguen una mejora de speedup. Estas implementaciones permiten simular para MIMO Masivo y de forma más rápida que por simulación convencional, un algo / La present tesi s'emmarca dins dels sistemes de comunicacions de múltiples antenes o sistemes MIMO. Avui dia, aquestos sistemes presenten una de les tecnologies més prometedora dins dels sistemes de comunicacions inalàmbriques. A través de l'ús de múltiples antenes en tots dos costats, transmissor y receptor, es pot augmentar la taxa de transmissió i la qualitat de la mateixa. D'altra banda, la tecnologia MIMO es pot utilitzar en un escenari multiusuari, on una estació base (BS) la qual està equipada amb diverses antenes serveix a diversos usuaris al mateix temps, aquests usuaris comparteixen dimensió espacial causant interferències multiusuari. Per totes aquestes raons, la tecnologia MIMO ha sigut adoptada en molts dels estàndars de comunicacions de nova generació. D'altra banda, la tecnologia MIMO Massiu, en la qual l'estació base està equipada amb un gran nombre d'antenes (centenars o milers) que serveix a molts usuaris en el mateix recurs de temps-freqüència. No obstant això, els avantatges proporcionats pels sistemes MIMO impliquen un augment en el cost computacional requerit. Per això, el disseny de receptors de baixa complexitat és una qüestió important en aquests sistemes. Per tal d'aconseguir esta finalitat, les principals contribucions de la tesi es basen en la implementació d'algoritmes de detecció soft i esquemes de precodificació eficients. En primer lloc, és abordat el problema de la detecció soft eficient en un sistema receptor sense interacció. Una descripció detallada dels detectors soft més emprats és presentada. D'altra banda, han sigut proposats dos algorismes de baix cost. El primer algorisme està basat en l'algorisme Box Optimization Hard Decoder (BOHD) i proporciona una baixa complexitat d'implementació aconseguint un bon resultat. El segon dels algorismes proposats intenta reduir el cost computacional del conegut algoritme Subspace Marginalization with Interference Suppression (SUMIS). En segon lloc, detectors d'entrada i eixidia soft (SISO, soft-input soft-output) els cuals són executats en estructures de recepció iterativa han sigut investigats. L'ocupació d'un receptor iteratiu millora el rendiment del sistema pel que fa a no realitzar realimentació, podent aconseguir la capacitat òptima. Per contra, el cost computacional es torna prohibitiu. En aquest context, tres algorismes han sigut presentats. Dos d'ells aconsegueixen un rendiment òptim, reduint la complexitat dels detectors SISO òptims que normalment són emprats. Per contra, l'altre algorisme aconsegueix un rendiment quasi òptim a baixa complexitat. En la tercera part, s'ha abordat el problema de la precodificació. S'ha dut a terme una anàlisi d'algunes de les tècniques de precodificació més usades, prestant especial atenció al seu rendiment i a la seua complexitat. Dins d'aquest context, l'impacte que el nombre de condició de la matriu de canal té en el rendiment dels precodificadors ha sigut avaluat. A més, aquest impacte ha sigut aprofitat per a proposar un precodificador híbrid , amb la finalitat de reduir la complexitat d'algorismes prèviament proposats. D'altra banda, en MIMO Massiu, un esquema precodificador ha sigut proposat. En l'última part, la implementació paral·lela de l'algorisme SUMIS és presentada. Diverses estratègies sobre la paral·lelizació de l'algorisme han sigut proposades i avaluades en dues plataformes diferents: multicore CPU i GPU. Les implementacions paral·leles aconsegueixen una millora de speedup quan el nombre d'àntenes o l'ordre de la constel·lació incrementen. D'aquesta manera, aquestes implementacions permeten simular per a MIMO Massiu, i de forma més ràpida que la simulació convencional. / Simarro Haro, MDLA. (2017). Effi cient algorithms for iterative detection and decoding in Multiple-Input and Multiple-Output Communication Systems [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/86186

Microsized hexagonal gallium nitride pyramids show promise as next generation Light Emitting Diodes (LEDs) due to certain quantum properties within the pyramids. One metric for evaluating the efficiency of a LED device is by studying its Light Extraction Efficiency (LEE). To calculate the LEE for different pyramid designs, simulations can be performed using the FDTD method. Maximizing the LEE is treated as a black-box optimization problem with an interpolation method that utilizes radial basis functions. A simple heuristic is implemented and tested for various pyramid parameters. The LEE is shown to be highly dependent on the pyramid size, the source position and the polarization. Under certain circumstances, a LEE over 17% is found above the pyramid. The results are however in some situations very sensitive to the simulation parameters, leading to results not converging properly. Establishing convergence for all simulation evaluations must be done with further care. The results imply a high LEE for the pyramids is possible, which motivates the need for further research.

Many algorithms today require a number of parameters to be set in order to perform well in a given application. The tuning of these parameters is often difficult and tedious to do manually, especially when the number of parameters is large. It is also unlikely that a human can find the best possible solution for difficult problems. To be able to automatically find good sets of parameters could both provide better results and save a lot of time. The prominent methods Bayesian optimization and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are evaluated for automatic parameter tuning in localization algorithms in this work. Both methods are evaluated using a localization algorithm on different datasets and compared in terms of computational time and the precision and recall of the final solutions. This study shows that it is feasible to automatically tune the parameters of localization algorithms using the evaluated methods. In all experiments performed in this work, Bayesian optimization was shown to make the biggest improvements early in the optimization but CMA-ES always passed it and proceeded to reach the best final solutions after some time. This study also shows that automatic parameter tuning is feasible even when using noisy real-world data collected from 3D cameras.

Názov práce: Evoluční algoritmy a aktivní učení Autor: Jakub Repický Katedra: Katedra teoretické informatiky a matematické logiky Vedúci diplomovej práce: doc. RNDr. Ing. Martin Holeňa, CSc., Ústav informa- tiky, Akademie věd České republiky Abstrakt: Vyhodnotenie ciel'ovej funkcie v úlohách spojitej optimalizácie často do- minuje výpočtovej náročnosti algoritmu. Platí to najmä v prípade black-box fun- kcií, t. j. funkcií, ktorých analytický popis nie je známy a ktoré sú vyhodnocované empiricky. Témou urýchl'ovania black-box optimalizácie s pomocou náhradných modelov ciel'ovej funkcie sa zaoberá vel'a autorov a autoriek. Ciel'om tejto dip- lomovej práce je vyhodnotit' niekol'ko metód, ktoré prepájajú náhradné modely založené na Gaussovských procesoch (GP) s Evolučnou stratégiou adaptácie ko- variančnej matice (CMA-ES). Gaussovské procesy umožňujú aktívne učenie, pri ktorom sú body pre vyhodnotenie vyberané s ciel'om zlepšit' presnost' modelu. Tradičné náhradné modely založené na GP zah'rňajú Metamodelom asistovanú evolučnú stratégiu (MA-ES) a Optimalizačnú procedúru pomocou Gaussovských procesov (GPOP). Pre účely tejto práce boli oba prístupy znovu implementované a po prvý krát vyhodnotené na frameworku Black-Box...