Dynamic Programming Approaches for Estimating and Applying Large-scale Discrete Choice Models

People go through their life making all kinds of decisions, and some of these decisions affect their demand for transportation, for example, their choices of where to live and where to work, how and when to travel and which route to take. Transport related choices are typically time dependent and characterized by large number of alternatives that can be spatially correlated. This thesis deals with models that can be used to analyze and predict discrete choices in large-scale networks. The proposed models and methods are highly relevant for, but not limited to, transport applications. We model decisions as sequences of choices within the dynamic discrete choice framework, also known as parametric Markov decision processes. Such models are known to be difficult to estimate and to apply to make predictions because dynamic programming problems need to be solved in order to compute choice probabilities. In this thesis we show that it is possible to explore the network structure and the flexibility of dynamic programming so that the dynamic discrete choice modeling approach is not only useful to model time dependent choices, but also makes it easier to model large-scale static choices. The thesis consists of seven articles containing a number of models and methods for estimating, applying and testing large-scale discrete choice models. In the following we group the contributions under three themes: route choice modeling, large-scale multivariate extreme value (MEV) model estimation and nonlinear optimization algorithms. Five articles are related to route choice modeling. We propose different dynamic discrete choice models that allow paths to be correlated based on the MEV and mixed logit models. The resulting route choice models become expensive to estimate and we deal with this challenge by proposing innovative methods that allow to reduce the estimation cost. For example, we propose a decomposition method that not only opens up for possibility of mixing, but also speeds up the estimation for simple logit models, which has implications also for traffic simulation. Moreover, we compare the utility maximization and regret minimization decision rules, and we propose a misspecification test for logit-based route choice models. The second theme is related to the estimation of static discrete choice models with large choice sets. We establish that a class of MEV models can be reformulated as dynamic discrete choice models on the networks of correlation structures. These dynamic models can then be estimated quickly using dynamic programming techniques and an efficient nonlinear optimization algorithm. Finally, the third theme focuses on structured quasi-Newton techniques for estimating discrete choice models by maximum likelihood. We examine and adapt switching methods that can be easily integrated into usual optimization algorithms (line search and trust region) to accelerate the estimation process. The proposed dynamic discrete choice models and estimation methods can be used in various discrete choice applications. In the area of big data analytics, models that can deal with large choice sets and sequential choices are important. Our research can therefore be of interest in various demand analysis applications (predictive analytics) or can be integrated with optimization models (prescriptive analytics). Furthermore, our studies indicate the potential of dynamic programming techniques in this context, even for static models, which opens up a variety of future research directions.

Dynamic Multi-Objective Optimization With jMetal and Spark: a Case Study

Technologies for Big Data and Data Science are receiving increasing research interest nowadays. This paper introduces the prototyping architecture of a tool aimed to solve Big Data Optimization problems. Our tool combines the jMetal framework for multi-objective optimization with Apache Spark, a technology that is gaining momentum. In particular, we make use of the streaming facilities of Spark to feed an optimization problem with data from different sources. We demonstrate the use of our tool by solving a dynamic bi-objective instance of the Traveling Salesman Problem (TSP) based on near real-time traffic data from New York City, which is updated several times per minute. Our experiment shows that both jMetal and Spark can be integrated providing a software platform to deal with dynamic multi-optimization problems.

Modeling and optimization techniques for advanced vehicular networking

This thesis deals with optimization techniques and modeling of vehicular networks. Thanks to the models realized with the integer linear programming (ILP) and the heuristic ones, it was possible to study the performances in 5G networks for the vehicular. Thanks to Software-defined networking (SDN) and Network functions virtualization (NFV) paradigms it was possible to study the performances of different classes of service, such as the Ultra Reliable Low Latency Communications (URLLC) class and enhanced Mobile BroadBand (eMBB) class, and how the functional split can have positive effects on network resource management. Two different protection techniques have been studied: Shared Path Protection (SPP) and Dedicated Path Protection (DPP). Thanks to these different protections, it is possible to achieve different network reliability requirements, according to the needs of the end user. Finally, thanks to a simulator developed in Python, it was possible to study the dynamic allocation of resources in a 5G metro network. Through different provisioning algorithms and different dynamic resource management techniques, useful results have been obtained for understanding the needs in the vehicular networks that will exploit 5G. Finally, two models are shown for reconfiguring backup resources when using shared resource protection.

Optimization of a polyhydroxyalkanoates production process using a halotolerant mixed microbial culture

The rate at which petroleum based plastics are being produced, used and thrown away is increasing every year because of an increase in the global population. Polyhydroxyalkanoates can represent a valid alternative to petroleum based plastics. They are biodegradable polymers that can be produced by some microorganisms as intracellular reserves. The actual problem is represented by the production cost of these bioplastics, which is still not competitive if compared to the one of petroleum based plastics. Mixed microbial cultures can be fed with substrates obtained from the acidogenic fermentation of carbon rich wastes, such as cheese whey, municipal effluents and various kinds of food wastes, that have a low or sometimes even inexisting cost and in this way wastes can be valorized instead of being discharged. The process consists of three phases: acidogenic fermentation in which the substrate is obtained, culture selection in which a PHA-storing culture is selected and enriched eliminating organisms that do not show this property and accumulation, in which the culture is fed until reaching the maximum storage capacity. In this work the possibility to make the process cheaper was explored trying to couple the selection and accumulation steps and a halotolerant culture collected from seawater was used and fed with an artificially salted synthetic substrated made of an aqueous solution containing a mixture of volatile fatty acids in order to explore also if its performance can allow to use it to treat substrates derived from saline effluents, as these streams cannot be treated properly by bacterias found in activated sludge plants due to inhibition caused by high salt concentrations. Generating and selling the produced PHAs obtained from these bacterias it could be possible to lower, nullify or even overcome the costs associated to the new section of a treating plant dedicated to saline effluents.

Phylogenetic position of the acariform mites: sensitivity to homology assessment under total evidence

Background: Mites (Acari) have traditionally been treated as monophyletic, albeit composed of two major lineages: Acariformes and Parasitiformes. Yet recent studies based on morphology, molecular data, or combinations thereof, have increasingly drawn their monophyly into question. Furthermore, the usually basal (molecular) position of one or both mite lineages among the chelicerates is in conflict to their morphology, and to the widely accepted view that mites are close relatives of Ricinulei. Results: The phylogenetic position of the acariform mites is examined through employing SSU, partial LSU sequences, and morphology from 91 chelicerate extant terminals (forty Acariformes). In a static homology framework, molecular sequences were aligned using their secondary structure as guide, whereby regions of ambiguous alignment were discarded, and pre-aligned sequences analyzed under parsimony and different mixed models in a Bayesian inference. Parsimony and Bayesian analyses led to trees largely congruent concerning infraordinal, well-supported branches, but with low support for inter-ordinal relationships. An exception is Solifugae + Acariformes (P. P = 100%, J. = 0.91). In a dynamic homology framework, two analyses were run: a standard POY analysis and an analysis constrained by secondary structure. Both analyses led to largely congruent trees; supporting a (Palpigradi (Solifugae Acariformes)) clade and Ricinulei as sister group of Tetrapulmonata with the topology (Ricinulei (Amblypygi (Uropygi Araneae))). Combined analysis with two different morphological data matrices were run in order to evaluate the impact of constraining the analysis on the recovered topology when employing secondary structure as a guide for homology establishment. The constrained combined analysis yielded two topologies similar to the exclusively molecular analysis for both morphological matrices, except for the recovery of Pedipalpi instead of the (Uropygi Araneae) clade. The standard (direct optimization) POY analysis, however, led to the recovery of trees differing in the absence of the otherwise well-supported group Solifugae + Acariformes. Conclusions: Previous studies combining ribosomal sequences and morphology often recovered topologies similar to purely morphological analyses of Chelicerata. The apparent stability of certain clades not recovered here, like Haplocnemata and Acari, is regarded as a byproduct of the way the molecular homology was previously established using the instrumentalist approach implemented in POY. Constraining the analysis by a priori homology assessment is defended here as a way of maintaining the severity of the test when adding new data to the analysis. Although the strength of the method advocated here is keeping phylogenetic information from regions usually discarded in an exclusively static homology framework; it still has the inconvenience of being uninformative on the effect of alignment ambiguity on resampling methods of clade support estimation. Finally, putative morphological apomorphies of Solifugae + Acariformes are the reduction of the proximal cheliceral podomere, medial abutting of the leg coxae, loss of sperm nuclear membrane, and presence of differentiated germinative and secretory regions in the testis delivering their products into a common lumen.

Flux Pinning Optimization of MgB(2) Bulk Samples Prepared Using High-Energy Ball Milling and Addition of TaB(2)

MgB(2) is considered to be an important conductor for applications. Optimizing flux pinning in these conductors can improve their critical currents. Doping can influence flux pinning efficiency and grain connectivity, and also affect the resistivity, upper critical field and critical temperature. This study was designed to attempt the doping of MgB(2) on the Mg sites with metal-diborides using high-energy ball milling. MgB(2) samples were prepared by milling pre-reacted MgB(2) and TaB(2) powders using a Spex 8000M mill with WC jars and balls in a nitrogen-filled glove box. The mixing concentration in (Mg(1-x)Ta(x))B(2) was up to x = 0.10. Samples were removed from the WC jars after milling times up to 4000 minutes and formed into pellets using cold isostatic pressing. The pellets were heat treated in a hot isostatic press (HIP) at 1000 degrees C under a pressure of 30 kpsi for 24 hours. The influence that milling time and TaB(2) addition had on the microstructure and the resulting superconducting properties of TaB(2)-added MgB(2) is discussed. Improvement J(c) of at high magnetic fields and of pinning could be obtained in milled samples with added TaB(2) The sample with added 5at.% TaB(2) and milled for 300 minutes showed values of J(c) similar to 7 x 10(5) A/cm(2) and F(p) similar to 14 GN/m(3) at 2T, 4.2 K. The milled and TaB(2)-mixed samples showed higher values of mu(0)H(irr) than the unmilled-unmixed sample.

Dynamic behavior analysis of drill-threading process when machining AISI Al-Si-Cu(4) alloy

Conventional threading operations involve two distinct machining processes: drilling and threading. Therefore, it is time consuming for the tools must be changed and the workpiece has to be moved to another machine. This paper presents an analysis of the combined process (drilling followed by threading) using a single tool for both operations: the tap-milling tool. Before presenting the methodology used to evaluate this hybrid tool, the ODS (operating deflection shapes) basics is shortly described. ODS and finite element modeling (FEM) were used during this research to optimize the process aiming to achieve higher stable machining conditions and increasing the tool life. Both methods allowed the determination of the natural frequencies and displacements of the machining center and optimize the workpiece fixture system. The results showed that there is an excellent correlation between the dynamic stability of the machining center-tool holder and the tool life, avoiding a tool premature catastrophic failure. Nevertheless, evidence showed that the tool is very sensitive to work conditions. Undoubtedly, the use of ODS and FEM eliminate empiric decisions concerning the optimization of machining conditions and increase drastically the tool life. After the ODS and FEM studies, it was possible to optimize the process and work material fixture system and machine more than 30,000 threaded holes without reaching the tool life limit and catastrophic fail.

Tailoring vibration mode shapes using topology optimization and functionally graded material concepts

Tailoring specified vibration modes is a requirement for designing piezoelectric devices aimed at dynamic-type applications. A technique for designing the shape of specified vibration modes is the topology optimization method (TOM) which finds an optimum material distribution inside a design domain to obtain a structure that vibrates according to specified eigenfrequencies and eigenmodes. Nevertheless, when the TOM is applied to dynamic problems, the well-known grayscale or intermediate material problem arises which can invalidate the post-processing of the optimal result. Thus, a more natural way for solving dynamic problems using TOM is to allow intermediate material values. This idea leads to the functionally graded material (FGM) concept. In fact, FGMs are materials whose properties and microstructure continuously change along a specific direction. Therefore, in this paper, an approach is presented for tailoring user-defined vibration modes, by applying the TOM and FGM concepts to design functionally graded piezoelectric transducers (FGPT) and non-piezoelectric structures (functionally graded structures-FGS) in order to achieve maximum and/or minimum vibration amplitudes at certain points of the structure, by simultaneously finding the topology and material gradation function. The optimization problem is solved by using sequential linear programming. Two-dimensional results are presented to illustrate the method.

Robust integration of real time optimization with linear model predictive control

Here, we study the stable integration of real time optimization (RTO) with model predictive control (MPC) in a three layer structure. The intermediate layer is a quadratic programming whose objective is to compute reachable targets to the MPC layer that lie at the minimum distance to the optimum set points that are produced by the RTO layer. The lower layer is an infinite horizon MPC with guaranteed stability with additional constraints that force the feasibility and convergence of the target calculation layer. It is also considered the case in which there is polytopic uncertainty in the steady state model considered in the target calculation. The dynamic part of the MPC model is also considered unknown but it is assumed to be represented by one of the models of a discrete set of models. The efficiency of the methods presented here is illustrated with the simulation of a low order system. (C) 2010 Elsevier Ltd. All rights reserved.

Real time optimization (RTO) with model predictive control (MPC)

This paper studies a simplified methodology to integrate the real time optimization (RTO) of a continuous system into the model predictive controller in the one layer strategy. The gradient of the economic objective function is included in the cost function of the controller. Optimal conditions of the process at steady state are searched through the use of a rigorous non-linear process model, while the trajectory to be followed is predicted with the use of a linear dynamic model, obtained through a plant step test. The main advantage of the proposed strategy is that the resulting control/optimization problem can still be solved with a quadratic programming routine at each sampling step. Simulation results show that the approach proposed may be comparable to the strategy that solves the full economic optimization problem inside the MPC controller where the resulting control problem becomes a non-linear programming problem with a much higher computer load. (C) 2010 Elsevier Ltd. All rights reserved.

A generalized multi-period mean-variance portfolio optimization with Markov switching parameters

In this paper, we deal with a generalized multi-period mean-variance portfolio selection problem with market parameters Subject to Markov random regime switchings. Problems of this kind have been recently considered in the literature for control over bankruptcy, for cases in which there are no jumps in market parameters (see [Zhu, S. S., Li, D., & Wang, S. Y. (2004). Risk control over bankruptcy in dynamic portfolio selection: A generalized mean variance formulation. IEEE Transactions on Automatic Control, 49, 447-457]). We present necessary and Sufficient conditions for obtaining an optimal control policy for this Markovian generalized multi-period meal-variance problem, based on a set of interconnected Riccati difference equations, and oil a set of other recursive equations. Some closed formulas are also derived for two special cases, extending some previous results in the literature. We apply the results to a numerical example with real data for Fisk control over bankruptcy Ill a dynamic portfolio selection problem with Markov jumps selection problem. (C) 2008 Elsevier Ltd. All rights reserved.

Forward-looking versus recursive-dynamic modeling in climate policy analysis: A comparison

This paper develops a multi-regional general equilibrium model for climate policy analysis based on the latest version of the MIT Emissions Prediction and Policy Analysis (EPPA) model. We develop two versions so that we can solve the model either as a fully inter-temporal optimization problem (forward-looking, perfect foresight) or recursively. The standard EPPA model on which these models are based is solved recursively, and it is necessary to simplify some aspects of it to make inter-temporal solution possible. The forward-looking capability allows one to better address economic and policy issues such as borrowing and banking of GHG allowances, efficiency implications of environmental tax recycling, endogenous depletion of fossil resources, international capital flows, and optimal emissions abatement paths among others. To evaluate the solution approaches, we benchmark each version to the same macroeconomic path, and then compare the behavior of the two versions under a climate policy that restricts greenhouse gas emissions. We find that the energy sector and CO(2) price behavior are similar in both versions (in the recursive version of the model we force the inter-temporal theoretical efficiency result that abatement through time should be allocated such that the CO(2) price rises at the interest rate.) The main difference that arises is that the macroeconomic costs are substantially lower in the forward-looking version of the model, since it allows consumption shifting as an additional avenue of adjustment to the policy. On the other hand, the simplifications required for solving the model as an optimization problem, such as dropping the full vintaging of the capital stock and fewer explicit technological options, likely have effects on the results. Moreover, inter-temporal optimization with perfect foresight poorly represents the real economy where agents face high levels of uncertainty that likely lead to higher costs than if they knew the future with certainty. We conclude that while the forward-looking model has value for some problems, the recursive model produces similar behavior in the energy sector and provides greater flexibility in the details of the system that can be represented. (C) 2009 Elsevier B.V. All rights reserved.

Lower Extremities Magnetic Resonance Angiography With Blood Pressure Cuff Compression: Quantitative Dynamic Analysis

Purpose: To quantitatively evaluate changes induced by the application of a femoral blood-pressure cuff (BPC) on run-off magnetic resonance angiography (MRA). which is a method generally previously proposed to reduce venous contamination in the leg. Materials and Methods: This study was Health Insurance Portability and Accountability Act (HIPAA)- and Institutional Review Board (IRB)-compliant, We used time-resolved gradient-echo gadolinium (Gd)-enhanced MRA to measure BPC effects on arterial, venous, and soft-tissue enhancement. Seven healthy volunteers (six men) were studied with the BPC applied at the mid-femoral level unilaterally using a 1.5T MR system after intravenous injection of Gd-BOPTA. Different statistical tools were used such as the Wilcoxon signed rank test and a cubic smoothing spline fit. Results: We found that BPC application induces delayed venous filling (as previously described), but also induces significant decreases in arterial inflow, arterial enhancement, vascular-soft tissue contrast, and delayed peak enhancement (which have not been previously measured). Conclusion: The potential benefits from using a BPC for run-off MRA must be balanced against the potential pitfalls, elucidated by our findings.

Self-optimization module for scheduling using case-based reasoning

Metaheuristics performance is highly dependent of the respective parameters which need to be tuned. Parameter tuning may allow a larger flexibility and robustness but requires a careful initialization. The process of defining which parameters setting should be used is not obvious. The values for parameters depend mainly on the problem, the instance to be solved, the search time available to spend in solving the problem, and the required quality of solution. This paper presents a learning module proposal for an autonomous parameterization of Metaheuristics, integrated on a Multi-Agent System for the resolution of Dynamic Scheduling problems. The proposed learning module is inspired on Autonomic Computing Self-Optimization concept, defining that systems must continuously and proactively improve their performance. For the learning implementation it is used Case-based Reasoning, which uses previous similar data to solve new cases. In the use of Case-based Reasoning it is assumed that similar cases have similar solutions. After a literature review on topics used, both AutoDynAgents system and Self-Optimization module are described. Finally, a computational study is presented where the proposed module is evaluated, obtained results are compared with previous ones, some conclusions are reached, and some future work is referred. It is expected that this proposal can be a great contribution for the self-parameterization of Metaheuristics and for the resolution of scheduling problems on dynamic environments.

Meta-heuristics tunning using CBR for dynamic scheduling

This paper addresses the problem of Biological Inspired Optimization Techniques (BIT) parameterization, considering the importance of this issue in the design of BIT especially when considering real world situations, subject to external perturbations. A learning module with the objective to permit a Multi-Agent Scheduling System to automatically select a Meta-heuristic and its parameterization to use in the optimization process is proposed. For the learning process, Casebased Reasoning was used, allowing the system to learn from experience, in the resolution of similar problems. Analyzing the obtained results we conclude about the advantages of its use.