Previsão multi-passos a frente do preço de energia elétrica de curto prazo no mercado brasileiro

A predição do preço da energia elétrica é uma questão importante para todos os participantes do mercado, para que decidam as estratégias mais adequadas e estabeleçam os contratos bilaterais que maximizem seus lucros e minimizem os seus riscos. O preço da energia tipicamente exibe sazonalidade, alta volatilidade e picos. Além disso, o preço da energia é influenciado por muitos fatores, tais como: demanda de energia, clima e preço de combustíveis. Este trabalho propõe uma nova abordagem híbrida para a predição de preços de energia no mercado de curto prazo. Tal abordagem combina os filtros autorregressivos integrados de médias móveis (ARIMA) e modelos de Redes Neurais (RNA) numa estrutura em cascata e utiliza variáveis explanatórias. Um processo em dois passos é aplicado. Na primeira etapa, as variáveis explanatórias são preditas. Na segunda etapa, os preços de energia são preditos usando os valores futuros das variáveis exploratórias. O modelo proposto considera uma predição de 12 passos (semanas) a frente e é aplicada ao mercado brasileiro, que possui características únicas de comportamento e adota o despacho centralizado baseado em custo. Os resultados mostram uma boa capacidade de predição de picos de preço e uma exatidão satisfatória de acordo com as medidas de erro e testes de perda de cauda quando comparado com técnicas tradicionais. Em caráter complementar, é proposto um modelo classificador composto de árvores de decisão e RNA, com objetivo de explicitar as regras de formação de preços e, em conjunto com o modelo preditor, atuar como uma ferramenta atrativa para mitigar os riscos da comercialização de energia.

Weibull and generalised exponential overdispersion models with an application to ozone air pollution

We consider the problem of estimating the mean and variance of the time between occurrences of an event of interest (inter-occurrences times) where some forms of dependence between two consecutive time intervals are allowed. Two basic density functions are taken into account. They are the Weibull and the generalised exponential density functions. In order to capture the dependence between two consecutive inter-occurrences times, we assume that either the shape and/or the scale parameters of the two density functions are given by auto-regressive models. The expressions for the mean and variance of the inter-occurrences times are presented. The models are applied to the ozone data from two regions of Mexico City. The estimation of the parameters is performed using a Bayesian point of view via Markov chain Monte Carlo (MCMC) methods.

Studio dei processi di ricarica naturale di corpi idrici sotterranei attraverso l'analisi di serie temporali

Nella Regione Emilia-Romagna, la zona delle conoidi ha una valenza strategica essendo la principale fonte di approvvigionamento idropotabile per le utenze civili, oltre che sostegno per le attività industriali ed agricole. All’interno di questo contesto ci si è soffermati sulla provincia di Piacenza, scegliendo come aree di studio le Conoidi del Trebbia e dell’Arda, per valutare le dinamiche di ricarica naturale attraverso l’identificazione della relazione che intercorre fra (i) l’entità dei deflussi superficiali riferiti ai corsi idrici che alimentano le conoidi, e (ii) il livello piezometrico nei rispettivi acquiferi. L’analisi è stata condotta applicando il modello Auto-Regressive Distributed Lag (ARDL).

Graphics Processor Unit Based Parallelization of Optimized Baseline Wander Filtering Algorithms for Long-term Electrocardiography

Long-term electrocardiogram (ECG) often suffers from relevant noise. Baseline wander in particular is pronounced in ECG recordings using dry or esophageal electrodes, which are dedicated for prolonged registration. While analog high-pass filters introduce phase distortions, reliable offline filtering of the baseline wander implies a computational burden that has to be put in relation to the increase in signal-to-baseline ratio (SBR). Here we present a graphics processor unit (GPU) based parallelization method to speed up offline baseline wander filter algorithms, namely the wavelet, finite, and infinite impulse response, moving mean, and moving median filter. Individual filter parameters were optimized with respect to the SBR increase based on ECGs from the Physionet database superimposed to auto-regressive modeled, real baseline wander. A Monte-Carlo simulation showed that for low input SBR the moving median filter outperforms any other method but negatively affects ECG wave detection. In contrast, the infinite impulse response filter is preferred in case of high input SBR. However, the parallelized wavelet filter is processed 500 and 4 times faster than these two algorithms on the GPU, respectively, and offers superior baseline wander suppression in low SBR situations. Using a signal segment of 64 mega samples that is filtered as entire unit, wavelet filtering of a 7-day high-resolution ECG is computed within less than 3 seconds. Taking the high filtering speed into account, the GPU wavelet filter is the most efficient method to remove baseline wander present in long-term ECGs, with which computational burden can be strongly reduced.

Pricing-to-market for UK export sector

This thesis investigates the pricing-to-market (PTM) behaviour of the UK export sector. Unlike previous studies, this study econometrically tests for seasonal unit roots in the export prices prior to estimating PTM behaviour. Prior studies have seasonally adjusted the data automatically. This study’s results show that monthly export prices contain very little seasonal unit roots implying that there is a loss of information in the data generating process of the series when estimating PTM using seasonally-adjusted data. Prior studies have also ignored the econometric properties of the data despite the existence of ARCH effects in such data. The standard approach has been to estimate PTM models using Ordinary Least Square (OLS). For this reason, both EGARCH and GJR-EGARCH (hereafter GJR) estimation methods are used to estimate both a standard and an Error Correction model (ECM) of PTM. The results indicate that PTM behaviour varies across UK sectors. The variables used in the PTM models are co-integrated and an ECM is a valid representation of pricing behaviour. The study also finds that the price adjustment is slower when the analysis is performed on real prices, i.e., data that are adjusted for inflation. There is strong evidence of auto-regressive condition heteroscedasticity (ARCH) effects – meaning that the PTM parameter estimates of prior studies have been ineffectively estimated. Surprisingly, there is very little evidence of asymmetry. This suggests that exporters appear to PTM at a relatively constant rate. This finding might also explain the failure of prior studies to find evidence of asymmetric exposure in foreign exchange (FX) rates. This study also provides a cross sectional analysis to explain the implications of the observed PTM of producers’ marginal cost, market share and product differentiation. The cross-sectional regressions are estimated using OLS, Generalised Method of Moment (GMM) and Logit estimations. Overall, the results suggest that market share affects PTM positively.Exporters with smaller market share are more likely to operate PTM. Alternatively, product differentiation is negatively associated with PTM. So industries with highly differentiated products are less likely to adjust their prices. However, marginal costs seem not to be significantly associated with PTM. Exporters perform PTM to limit the FX rate effect pass-through to their foreign customers, but they also avoided exploiting PTM to the full, since to do so can substantially reduce their profits.

A dinâmica da taxa de câmbio no Brasil face às operações swap (2002-2015)

This dissertation investigates, based on the Post-Keynesian theory and on its concept of monetary economy of production, the exchange rate behavior of the Brazilian Real in the presence of Brazilian Central Bank's interventions by means of the so-called swap transactions over 2002-2015. Initially, the work analyzes the essential properties of an open monetary economy of production and, thereafter, it presents the basic propositions of the Post-Keynesian view on the exchange rate determination, highlighting the properties of foreign exchange markets and the peculiarities of the Brazilian position into the international monetary and financial system. The research, thereby, accounts for the various segments of the Brazilian foreign exchange market. To accomplish its purpose, we first do a literature review of the Post-Keynesian literature about the topic. Then, we undertake empirical exams of the exchange rate determination using two statistical methods. On the one hand, to measure the volatility of exchange rate, we estimate Auto-regressive Conditional Heteroscedastic (ARCH) and Generalized Auto-regressive Conditional Heteroscedastic (GARCH) models. On the other hand, to measure the variance of the exchange rate in relation to real, financial variables, and the swaps, we estimate a Vector Auto-regression (VAR) model. Both experiments are performed for the nominal and real effective exchange rates. The results show that the swaps respond to exchange rate movements, trying to offset its volatility. This reveals that the exchange rate is, at least in a certain magnitude, sensitive to swaps transactions conducted by the Central Bank. In addition, another empirical result is that the real effective exchange rate responds more to the swaps auctions than the nominal rate.

An empirical investigation of the impact of global energy transition on Nigerian oil and gas exports

18 months embargo on the thesis and check appendix for copy right materials

SRAE: Sustainable Regressive Auto Encoder

Al giorno d’oggi viviamo in una realtà dove lo sviluppo economico, l’innovazione tecnologica, la qualità della vita e l’impatto ambientale sono i protagonisti assoluti. Tutti, persino gli Stati del mondo, si trovano a fare i conti con varie problematiche riguardanti i quattro aspetti sopracitati e qui possiamo dire che la sostenibilità ne è il punto chiave e che al momento non sembra esistere ancora una metrica riconosciuta e approvata per consigliare, a chi di interesse, come modificare certi aspetti per crescere in modo sostenibile. Le Nazioni Unite hanno deciso, di comune accordo, di stilare una lista di obiettivi da raggiungere entro il 2030 dove è possibile trovare argomenti in linea con quanto descritto finora. Questa raccolta è principalmente divisa in aspetti economici, sociali e ambientali che sono le stesse categorie di dati impiegate per il calcolo del Sustainable Development Index. In questo elaborato ci si propone di progettare e sviluppare una rete neurale predittiva da affiancare a un sistema di feedback per realizzare un prodotto che sia abile di: descrivere il contesto di partenza tramite l’SDI e/o consigliare comportamenti per migliorare la situazione in modo sostenibile.

Modélisation de l'interprétation des pianistes & applications d'auto-encodeurs sur des modèles temporels

Ce mémoire traite d'abord du problème de la modélisation de l'interprétation des pianistes à l'aide de l'apprentissage machine. Il s'occupe ensuite de présenter de nouveaux modèles temporels qui utilisent des auto-encodeurs pour améliorer l'apprentissage de séquences. Dans un premier temps, nous présentons le travail préalablement fait dans le domaine de la modélisation de l'expressivité musicale, notamment les modèles statistiques du professeur Widmer. Nous parlons ensuite de notre ensemble de données, unique au monde, qu'il a été nécessaire de créer pour accomplir notre tâche. Cet ensemble est composé de 13 pianistes différents enregistrés sur le fameux piano Bösendorfer 290SE. Enfin, nous expliquons en détail les résultats de l'apprentissage de réseaux de neurones et de réseaux de neurones récurrents. Ceux-ci sont appliqués sur les données mentionnées pour apprendre les variations expressives propres à un style de musique. Dans un deuxième temps, ce mémoire aborde la découverte de modèles statistiques expérimentaux qui impliquent l'utilisation d'auto-encodeurs sur des réseaux de neurones récurrents. Pour pouvoir tester la limite de leur capacité d'apprentissage, nous utilisons deux ensembles de données artificielles développées à l'Université de Toronto.

Uma abordagem dirigida por modelos para desenvolvimento de middlewares auto-adaptativos para transmissão de fluxo de dados baseado em restrições de QoS

The use of middleware technology in various types of systems, in order to abstract low-level details related to the distribution of application logic, is increasingly common. Among several systems that can be benefited from using these components, we highlight the distributed systems, where it is necessary to allow communications between software components located on different physical machines. An important issue related to the communication between distributed components is the provision of mechanisms for managing the quality of service. This work presents a metamodel for modeling middlewares based on components in order to provide to an application the abstraction of a communication between components involved in a data stream, regardless their location. Another feature of the metamodel is the possibility of self-adaptation related to the communication mechanism, either by updating the values of its configuration parameters, or by its replacement by another mechanism, in case of the restrictions of quality of service specified are not being guaranteed. In this respect, it is planned the monitoring of the communication state (application of techniques like feedback control loop), analyzing performance metrics related. The paradigm of Model Driven Development was used to generate the implementation of a middleware that will serve as proof of concept of the metamodel, and the configuration and reconfiguration policies related to the dynamic adaptation processes. In this sense was defined the metamodel associated to the process of a communication configuration. The MDD application also corresponds to the definition of the following transformations: the architectural model of the middleware in Java code, and the configuration model to XML

Processos auto-organizados em agregados de larvas de moscas-varejeiras em dispersão pós-alimentar: experimentação, modelagem e validação

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Análise de teses internalistas subjacentes à modelagem computacional da mente em uma perspectiva situada, incoporada e auto organizada

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Métodos de previsão auto-regressivo aplicado a uma série de volume de produção de caminhões

The national truck fleet has expanded strongly in recent decades. However, due to fluctuations in the demand that the market is exposed, it needed up making more effective strategic decisions of automakers. These decisions are made after an evaluation of guaranteed sales forecasts. This work aims to generate an annual forecast of truck production by Box and Jenkins methodology. They used annual data for referring forecast modeling from the year 1957 to 2014, which were obtained by the National Association of Motor Vehicle Manufacturers (Anfavea). The model used was Autoregressive Integrated Moving Average (ARIMA) and can choose the best model for the series under study, and the ARIMA (2,1,3) as representative for conducting truck production forecast

Aplicação do valor presente ajustado (APV) para avaliação do fluxo de caixa de uma empresa do setor automotivo no sistema inovar auto

The automobile industry shows relevance inside the Brazilian industrial scenario since it contributes with the development of a significant chain of supply, distributors, workshops, publicity agencies and insurance companies in the internal market, aside from being one of the five biggest worldwide market. Thereby, the federal government decreed in Dec, 17th 2012 by Law nº 12.715 the Inovar-Auto Program. As the Adjusted Present Value (APV) is highly recommended, although not yet widespread to public politics of tax reduction, this work intends to apply the APV method on the cash flow analysis of an automobile sector's company, which has recently installed in national territory and wants to rely with governmental incentives proposed by Inovar-Auto Program. The developed work evaluates the company's current cash flow stochastically from mathematical modeling of variables such as price, demand and interest rate through probability distributions with the assist of Crystal Ball software, a Microsoft Excel Add-in, generating different scenarios from Monte Carlo Simulation. As results probabilities situations have been evaluated until the end of the Inovar-Auto's conducted period, in 2017. Beside APV others indicator such as Internal Rate of Return (IRR) and payback period were estimated for the investment project. For APV a sampling distribution with only 0.057% of risk, IRR of 29% were obtained and estimated project payback period was 4.13 years

Métodos de previsão auto-regressivo aplicado a uma série de volume de produção de caminhões

The national truck fleet has expanded strongly in recent decades. However, due to fluctuations in the demand that the market is exposed, it needed up making more effective strategic decisions of automakers. These decisions are made after an evaluation of guaranteed sales forecasts. This work aims to generate an annual forecast of truck production by Box and Jenkins methodology. They used annual data for referring forecast modeling from the year 1957 to 2014, which were obtained by the National Association of Motor Vehicle Manufacturers (Anfavea). The model used was Autoregressive Integrated Moving Average (ARIMA) and can choose the best model for the series under study, and the ARIMA (2,1,3) as representative for conducting truck production forecast