Many control systems of practical importance are multivariable. In such systems, each manipulated variable (input signal) may affect several controlled variables (output signals) causing interaction between the input/output loops. For this reason, control of multivariable systems is typically much more difficult compared to the single-input single-output case. It is therefore of great importance to quantify the degree of interaction so that proper input/output pairings that minimize the impact of the interaction can be formed. For this, dedicated interaction measures can be used. The first part of this thesis treats interaction measures. The commonly used Relative Gain Array (RGA) is compared with the Gramian-based interaction measures the Hankel Interaction Index Array (HIIA) and the Participation Matrix (PM) which consider controllability and observability to quantify the impact each input signal has on each output signal. A similar measure based on the <img src="http://www.diva-portal.org/cgi-bin/mimetex.cgi?%5Cmathcal%20H_2" /> norm is also investigated. Further, bounds on the uncertainty of the HIIA and the PM in case of uncertain models are derived. It is also shown how the link between the PM and the Nyquist diagram can be utilized to numerically calculate such bounds. Input/output pairing strategies based on linear quadratic Gaussian (LQG) control are also suggested. The key idea is to design single-input single-output LQG controllers for each input/output pair and thereafter form closed-loop multivariable systems for each control configuration of interest. The performances of these are compared in terms of output variance. In the second part of the thesis, the activated sludge process, commonly found in the biological wastewater treatment step for nitrogen removal, is considered. Multivariable interactions present in this type of bioreactor are analysed with the tools discussed in the first part of the thesis. Furthermore, cost-efficient operation of the activated sludge process is investigated.

The combination of two or more portfolio rules is theoretically convex in return-risk space, which provides for a new class of portfolio rules that gives purpose to the Mean-Variance framework out-of-sample. The author investigates the performance loss from estimation risk between the unconstrained Mean-Variance portfolio and the out-of-sample Global Minimum Variance portfolio. A new two-fund rule is developed in a specific class of combined rules, between the equally weighted portfolio and a mean-variance portfolio with the covariance matrix being estimated by linear shrinkage. The study shows that this rule performs well out-of-sample when covariance estimation error and bias are balanced. The rule is performing at least as good as its peer group in this class of combined rules.

The optimal steady-state control, and suboptimal adaptive control, of disturbed single-input-output systems are introduced, and the class of systems considered is defined. It is noted that the stochastic tracking problem divides into a deterministic tracking problem and a stochastic regulator problem; the solutions to these two problems are shown to be independent but formally similar. The continuous regulator problem is approached via both frequency and time domain methods: the former method is extended to cover unstable systems; the latter method is extended to include systems with input delay. The two regulators are shown to be externally equivalent. The frequency domain method is briefly described for discrete systems, and shown to include the minimum variance regulator of Åström and Peterka as a special case. Some systems which allow measurement noise to be treated as a system disturbance for the purposes of optimal controller design are investigated. A novel class of control laws is described in both continuous and discrete time; in the same way as the minimum variance regulator forms the basis of the self-tuning regulator of Åström and Wittenmark, these minimum variance controllers from the basis of a self-tuning controller. These minimum variance controllers have a number of advantages over the minimum-variance regulator, and are open to a number of interpretations including: a model following control law, and an extension of classical control laws to systems with delay. The optimality of this class of control laws is investigated, and analogies drawn with the previously considered k-step-ahead control laws; some examples are given to illustrate the method. An adaptive control law combining the above minimum variance controllers with a linear least-squares algorithm is proposed and shown to be self-tuning. These self-tuning controllers are only slightly more complex than the self-tuning regulator of Åström and Wittenmark, but have a number of advantages. Intuitive justification is given for the conjecture that some methods of Ljung, developed for the analysis of the self-tuning regulator, are applicable to the self-tuning controller. Simulated examples are given which compare and contrast the performance of the self-tuning controller with that of the self-tuning regulator. The first steps towards a quasi-continuous self-tuning controller are outlined.

Made available in DSpace on 2010-04-20T21:00:30Z (GMT). No. of bitstreams: 4 nicolauassali.pdf.jpg: 21057 bytes, checksum: e49c3a73a969030bb30a7b487e8ddf77 (MD5) nicolauassali.pdf: 745103 bytes, checksum: dcb827d78438926dd042deccffc5bab4 (MD5) 1_136970.pdf: 745134 bytes, checksum: 17ea1cc72a370b8ea2ba2cf6590ebe16 (MD5) nicolauassali.pdf.txt: 258686 bytes, checksum: 416660ae630d51947f844cef8a94fb45 (MD5) Previous issue date: 2008-02-13T00:00:00Z / This dissertation analyses the performance and features of some of the current Brazilian funds of funds, called multimanagers, as well as the performance of funds of funds as a result of the simulation of Brazilian funds portfolios that use several investment strategies known as multimarkets. The diversification through a multimarkets funds portfolio involves other variables beyond the traditional approach of mean-variance. The first part of this study presents the main features of the selected funds of funds and also describes more than the mean-variance, showing the third and fourth moments of the returns distribution. The second part uses the tool named Style Analysis (Sharpe, 1988) in order to determine the return exposure of each of the funds of funds of the sample to certain asset classes. In this study were chosen the following asset classes: Ibovespa, CDI, Dollar and IRF-M. Through the medium-variance approach, the third part of this study uses a tool known as the Portfolio Theory (Markowitz, 1952) as the minimum variance frontier, in order to evaluate the performance of each funds of funds in the given sample. The performance is evaluated on the comparison basis of the minimum variance frontier built from a benchmark portfolio (comprising two of the major Brazilian financial assets of low and high risk: CDI and Ibovespa, respectively) with another minimum variance frontier built from the addition of a fund of funds into the benchmark portfolio. The last part refers to simulations of multimarkets portfolio funds that allow the allocation of variable income in the portfolio and it also allows the use of leverage. The goal is to check through the return of the average values, variance, asymmetry and kurtosis, the efficiency of such funds as instruments of diversification. The outcomes show that the 32 multimanager funds of funds analyzed do not have normal return distribution and 29 ones present negative skewness behavior. The Style Analysis indicates high sensibility to CDI and IRF-M, and low sensibility to Ibovespa and Dollar, main financial market indexes. The majority of multimanager funds of funds improved the Minimum Variance Frontier when added to a reference portfolio (CDI + Ibovespa), in other words, there was a reduction on risk – return relation. The portfolio simulation indicates that in the last three years the multimarkets funds classified as Leveraged Variable Income has been more aggressive in the strategies due to the asymmetry behavior; however this kurtosis behavior indicates a position not too aggressive as well. So the construction of Funds portfolios that use several investment strategies should not be restraint to the mean-variance approach. It should also involve asymmetry, kurtosis and investor preferences. / Esta dissertação analisa o desempenho e as características de uma parte dos atuais fundos de fundos brasileiros, os denominados multigestores, bem como o desempenho de fundos de fundos resultantes da simulação de carteiras de fundos brasileiros que utilizam várias estratégias de investimentos, conhecidos como multimercados. A diversificação através de uma carteira de fundos multimercados envolve outras variáveis além da tradicional abordagem de média-variância. A primeira parte do estudo apresenta as principais características dos fundos de fundos selecionados e descreve, além da média e variância, o terceiro e quarto momentos das distribuições dos retornos. A segunda parte utiliza a ferramenta chamada Análise de Estilo (Sharpe, 1988), para determinar a exposição dos retornos de cada um dos fundos de fundos da amostra a determinadas classes de ativos. Neste trabalho foram escolhidas as seguintes classes de ativos: Ibovespa, CDI, Dólar e IRF-M. Através da abordagem de média-variância, a terceira parte do estudo utiliza a ferramenta conhecida na Teoria da Carteira (Markowitz, 1952) como fronteira de mínima variância, para avaliar o desempenho de cada um dos fundos de fundos da amostra. O desempenho é avaliado com base na comparação da fronteira de mínima variância construída a partir de uma carteira de referência (composta por dois dos principais ativos financeiros brasileiros de baixo e alto risco: CDI e Ibovespa, respectivamente) com outra fronteira de mínima variância construída a partir do acréscimo de um fundo de fundos à carteira de referência. A última parte refere-se a simulações de carteiras de fundos multimercados que permitem a alocação de renda variável na carteira e também permitem o uso de alavancagem. Seu objetivo é verificar, através dos valores de retorno médio, variância, assimetria e curtose, a eficiência desses fundos como instrumentos de diversificação. Os resultados mostram que os 32 fundos de fundos multigestores analisados não tem distribuição normal de retornos e 29 apresentam assimetria negativa. A Análise de Estilo indica grande sensibilidade ao CDI e ao IRF-M, e pouca sensibilidade ao Ibovespa e Dólar, importantes índices do mercado financeiro. A maioria dos fundos de fundos multigestores melhorou a Fronteira Eficiente quando adicionados a uma carteira de referência (CDI + Ibovespa), ou seja, houve uma redução na relação risco-retorno. A simulação das carteiras indica que nos últimos três anos os fundos multimercados classificados como Com Renda Variável Com Alavancagem tem sido mais agressivos nas estratégias, devido ao comportamento da assimetria, porém o comportamento da curtose indica também uma posição nem tão agressiva. Logo, a construção de carteiras com fundos que utilizam diversas estratégias de investimentos não deve se restringir à abordagem de média-variância. Deve também envolver também assimetria, curtose e preferências do investidor.

nÃo hà / Quando a conjuntura econÃmica de um paÃs propicia baixa taxa de juros de mercado, a rentabilidade de aplicaÃÃes ditas seguras, como em renda fixa, deixa de ser negÃcio atrativo para investidores, que optam por submeter-se a um risco maior em busca de maiores rendimentos. Em tais cenÃrios, investidores arriscam-se no mercado acionÃrio, no qual ganhos maiores podem ser auferidos, apesar do risco superior ao da renda fixa. A Teoria Moderna do PortfÃlio mostra que esse risco pode ser reduzido pela diversificaÃÃo de ativos. Esta pesquisa tem por objetivo verificar se um modelo quantitativo baseado na Teoria Moderna do PortfÃlio à capaz ajudar na diversificaÃÃo de um portfÃlio, reduzindo risco a nÃveis inferiores aos da carteira de mercado, enquanto proporciona rendimentos superiores aos de s de mercado. Os testes utilizaram sÃries histÃricas de 36 ativos negociados na BOVESPA entre 1999 e 2012, e foram conduzidos em janelas de amostras de 12, 36, 60 e 120 observaÃÃes. Os resultados mostram que a ampliaÃÃo do horizonte de investimento permite a obtenÃÃo de desempenho superior do portfÃlio selecionado pela otimizaÃÃo baseada na mÃnima variÃncia, comparativamente à aplicaÃÃo livre de risco (CDI) e ao Ãndice Bovespa.

資產配置問題與方法一直是投資人所關心之重要課題。藉由不同之建構投資組合的方法尋找資產的最適權重分配，可使得投資人對所持有資產的管理變得更容易且具效率。在這些方法當中，最小變異數投資組合可滿足追求風險極小化之需求。本文亦從此出發，探討一種特殊的最小變異數投資組合：加權範數最小變異數投資組合，並以台灣50作為實證資料，運用十個績效指標來衡量加權範數最小變異數投資組合、其他三種標竿投資組合與指數型基金台灣50之表現。 結果發現本研究所選取之台灣市場資料在運用加權範數最小變異數投資組合下，確實可以打敗其他大部分投資組合以及台灣50基金，並且在以下兩論點與過往文獻之敘述一致：加入報酬限制條件無法改善績效、使用替代參數亦可提供相稱績效。 / The asset allocation problem has always been an important issue on which investors concern. It is easier and more efficient for investors to manage their assets through constructing their portfolios in different methods to find the most optimized weight of assets. This essay explores a special portfolio, Weighted-Norm Minimum Variance Portfolio (WNMVP), which can minimize the risks of investment, and use Taiwan stock market data to undertake empirical study. The research measured the performance of WNMVP, other three benchmark portfolios, and Taiwan Top 50 ETF (0050) by using ten indicators, bringing three findings. First, WNMVP performs better than most of other portfolios do. Second, adding estimated mean return vector into the WNMVP does not improve performances. Third, three alternative norm penalties provide comparable performance as parameters in WNMVP do. The second and third findings are consistence with previous literature.

No description available.

This thesis proposes an intelligent multiple-controller framework for complex systems that incorporates a fuzzy logic based switching and tuning supervisor along with a neural network based generalized learning model (GLM). The framework is designed for adaptive control of both Single-Input Single-Output (SISO) and Multi-Input Multi-Output (MIMO) complex systems. The proposed methodology provides the designer with an automated choice of using either: a conventional Proportional-Integral-Derivative (PID) controller, or a PID structure based (simultaneous) Pole and Zero Placement controller. The switching decisions between the two nonlinear fixed structure controllers is made on the basis of the required performance measure using the fuzzy logic based supervisor operating at the highest level of the system. The fuzzy supervisor is also employed to tune the parameters of the multiple-controller online in order to achieve the desired system performance. The GLM for modelling complex systems assumes that the plant is represented by an equivalent model consisting of a linear time-varying sub-model plus a learning nonlinear sub-model based on Radial Basis Function (RBF) neural network. The proposed control design brings together the dominant advantages of PID controllers (such as simplicity in structure and implementation) and the desirable attributes of Pole and Zero Placement controllers (such as stable set-point tracking and ease of parameters’ tuning). Simulation experiments using real-world nonlinear SISO and MIMO plant models, including realistic nonlinear vehicle models, demonstrate the effectiveness of the intelligent multiple-controller with respect to tracking set-point changes, achieve desired speed of response, prevent system output overshooting and maintain minimum variance input and output signals, whilst penalising excessive control actions.

Most indexes use a cap-weighted strategy as the asset allocation method. Many researchers suggest that although the cap-weighted strategy often serves as an appropriate surrogate to the market portfolio, it cannot consistently outperform other portfolio weighting strategies. The main reasons behind it would be related to the market movement and the underlying volatility. It is possible to narrow down the scope of the research by focusing on an industry index as was done in this research. The focus would be on the mining index of Indonesia. Comparisons will be done between the established index to other portfolio weighting schemes, namely the equally weighted portfolio and the minimum variance portfolio. The results of the research was that the index was not quite efficient, both on the returns and the Sharpe or information ratio aspect. There are many possible reasons behind this, but the most possible reasons would be that the stocks included do not contribute to diversification, over focus on the coal industry, lack of rebalancing or restructuring, in addition to the market itself. The implication of this research would be that stock exclusion might also contribute to risk minimization.

The aim of this study was to assess the feasibility of constructing optimal portfolios using the Johannesburg Securities Exchange tradable sector indices. Three indices were employed, namely Financials, Industrials and Resources and were benchmarked against the JSE All Share Index for the period January 2007 to December 2017. The period was split into three, namely before the 2007-2009 global financial crises, during the global financial crises and after the global financial crises. The Markowitz’s mean-variance optimisation framework was employed for the construction of global mean variance portfolios. The results of this study showed that it was feasible to construct mean-variance efficient portfolios using tradable sector indices from the Johannesburg Securities Exchange. It was also established that, on the other hand, global mean variance portfolios constructed in this study, outperformed the benchmark index in a bullish market in terms of the risk-return combinations. On the other hand, in bear markets, the global mean variance portfolios were observed to perform better than the benchmark index in terms of risk. Further, the results of the study showed that portfolios constructed from the three tradable indices yielded diversification benefits despite their positive correlation with each other. The results of the study corroborate the findings by other scholars that the mean-variance optimisation framework is effective in the construction of optimal portfolios using the Johannesburg Securities Exchange. The study also demonstrated that Markowitz’s mean-variance framework could be applied by investors faced with a plethora of investment choices to construct efficient portfolios utilising the Johannesburg Securities Exchange tradable sector indices to achieve returns commensurate with their risk preferences. / Business Management / M. Com. (Business Management)