Made available in DSpace on 2014-07-29T15:13:38Z (GMT). No. of bitstreams: 1 Tese_Luciano Muniz.pdf: 1589101 bytes, checksum: 4ed47c785cea4fb76d874ca98dbd4467 (MD5) Previous issue date: 2010-07-30 / When approaching the crop-livestock integration (CLI) theme, the present thesis had as one of its main objectives to evaluate the alterations in the soil-plantanimal- environment components exercised by the crop and pasture rotation dynamics in crop and livestock integration system. Two adjacent areas, one representing the natural environment (original cerrado vegetation) and other the degraded pastures served as reference ( control ) to the inferences performed. The experiment was performed at a 92 ha area, divided into six paddocks of approximately 15 ha, where the annual crops and pastures rotation was made. The soil samplings were collected at the 0-10, 10-20, 20-30, 30-40 and 40-50 cm layers. There was an increase in the carbon contents of the microbial biomass, in the microbial quotient and in the organic matter on the soil and reduction in the metabolic quotient at the pastures chronological sequence environments, at the crop-livestock integration system, in comparison with the degraded pasture. The different pastures stages within the crop-livestock integration system stocked the average of 17,67 Mg ha-1 carbon more than the degraded pasture up to a 50 cm depth. The Cerrado contained the most carbon stock and the degraded pasture the least among all the environments studied. There was a significant decrease in the phosphor and potassium contents in relation to the pasture age increase and an increase in the calcium and magnesium contents. Micronutrients contents among the treatments evaluated presented values above the demand for capim- Marandu. The capim-Marandu samplings were performed in five different seasons of the year (winter, beginning and end of spring, summer and autumn). Quantitative and qualitative alterations at the forage were observed during the experimental period. Changes on the structural components green leaf, green stem and dead material, as well as on DM (Dry Matter), GP (Gross Protein), TDN (Total Digestive Nutrients) and FND (Fiber in Neutral Detergent) contents, among others, characterized the forage on the different periods. The qualitative variations among the forages are of high magnitude, being outlined the significant drop on GP (Gross Protein) and TDN (Total Digestive Nutrients) contents according to the pasture maturity development. All pastures chronological sequence treatments, after 2,5 years of crop, resulted in favorable evaluations, having P1 treatment as the best investment option with NPV (Net Present Value) equals to R$144,34 followed by P2 treatment with R$112,61 and P3 with R$58,54, indicating to be a favorable Project. There is indication on the present work that the biggest loss in relation to the obtained economic advantages happens already from the second year after the pastures establishment. Such results may constitute important implications at CLI systems planning. Carbon bonus at pasture based animal production system may be a financial incentive for the producer to join the pastures rotation with annual crops. Nevertheless it is necessary that studies are performed to quantify emissions of gases responsible for greenhouse in order to verify whether the result represents a bonus or an environmental onus to the producer. / A presente tese, ao abordar o tema integração lavoura-pecuária (ILP), teve como um de seus principais objetivos avaliar as alterações nos componente solo-planta-animal-ambiente exercidas pela dinâmica de rotação de culturas e pastagens em sistema de integração lavoura e pecuária. Duas áreas adjacentes, uma representativa do meio ambiente natural (vegetação de cerrado original ) e outra de pastagens degradadas, serviram de referência ( controle ) às inferências realizadas. O experimento foi realizado numa área de 92 ha, dividida em seis piquetes de aproximadamente 15 ha, onde foi feita a rotação de culturas anuais e pastagens. As amostras de solo foram coletadas nas camadas 0-10, 10-20, 20-30, 30-40 e 40-50 cm. Houve aumento nos teores de carbono da biomassa microbiana, no quociente microbiano e na matéria orgânica no solo e redução no quociente metabólico nos ambientes da cronossequência das pastagens, no sistema integração lavoura-pecuária, em comparação com a pastagem degradada. As diferentes fases das pastagens dentro do sistema de integração lavoura-pecuária estocaram, em média, 17,67 Mg ha-1 mais carbono que a pastagem degradada até a profundidade de 50 cm. O Cerrado conteve o maior, e a pastagem degradada o menor estoque de carbono entre todos os ambientes estudados. Houve um decréscimo significativo nos teores de fósforo e potássio com o aumento da idade da pastagem e aumento nos teores de cálcio e magnésio. Os teores dos micronutrientes entre os tratamentos avaliados apresentaram valores acima da exigência para o capim-Marandu. As amostras de capim-Marandu foram realizadas em cinco épocas do ano (inverno, início e final da primavera, verão e outono). Alterações quantitativas e qualitativas na forragem foram observadas durante o período experimental. Mudanças nos componentes estruturais folha verde, colmo verde e material morto, bem como nos teores de matéria seca (MS), proteína bruta (PB), nutrientes disponíveis totais (NDT) e fibra em detergente neutro (FDN), entre outros, caracterizaram a forragem nos diferentes períodos. As variações qualitativas entre as forrageiras são de alta magnitude, destacando-se a queda significativa nos teores de PB e NDT, com o avanço da maturidade da pastagem. Todos os tratamentos da cronossequência das pastagens, após 2,5 anos de lavoura, resultaram em avaliações favoráveis, sendo o tratamento P1 a melhor opção de investimento, com valor presente líquido (VPL) igual a R$ 144,34, seguido pelo tratamento P2 com R$ 112,61 e P3 com R$ 58,54, indicando tratar-se de projeto favorável. Há indicação no presente trabalho que a maior perda em relação às vantagens econômicas obtidas ocorre já a partir do segundo ano após o estabelecimento das pastagens, podendo constituir implicações importantes no planejamento de sistemas de ILP. O bônus de carbono no sistema de produção animal a pasto pode ser um incentivo financeiro para o produtor aderir à rotação de pastagens com culturas anuais. Porém é preciso que sejam realizados estudos que quantifiquem as emissões de gases responsáveis pelo efeito estufa, para verificar se o balanço representa um bônus ou um ônus ambiental para o produtor.

In most of the urban cities of developing countries piped water supply is intermittent and they receive water on alternate days for about few hours. The Unaccounted For Water (UFW) in these cities is very high due to aged infrastructure, poor management and operation of the system. In the cities of developing countries, supplied water is not able to meet the demand and there is huge gap between supply and demand of water. To meet the water demand people are depending on other sources of water like groundwater, rain water harvesting, waste water treatment, desalination etc. Huge quantity of groundwater is extracted without any account for the quantity of water used. The main challenge for water authorities is to meet the consumer demands at varying loading conditions. However, the present execution of decisions in the operational management of WDS is through manual control. The manual control of valve throttling and control of pump speed, reduces the efficiency and operation of WDS. In such cases, system modeling coupled with automated control can play a significant role in the appropriate execution and operation of the system. In the past few decades, there has been a major development in the field of modeling and analysing water distribution systems. Most of the people in Indian mega cities are facing water problems as they are not able to receive safe reliable drinking water. In rapidly growing cities, the water resources management has been a major concern for the Government. There is always a need to optimize the available water resources when the rate of demand constantly beats the rate of replenishments. Mathematical modeling of WDS has become an indispensible tool since the ages to model any type of WDS. Development of mathematical models of WDS is necessary to analyse the system behavior for a wide range of operating conditions. Using models, problems can be anticipated in proposed or existing systems, and solutions can be evaluated before time, money, and materials are invested in a real-world project. In the present study, we have developed a model of WDS of a typical city like Bangalore, India and analysed them for several scenarios and operating conditions. Bangalore WDS is modeled using EPANET. Before a network model is used for analysis purpose, it must be ensured that the model is predicting the behavior of the system with reasonable accuracy. The process of matching the parameters of the developed model and the field observed data is known as calibration. All WDS require calibration for effective modeling and simulation of the system. Demand and roughness are the most uncertain parameters and they are adjusted repeatedly to get the required head at nodes and flow in the pipes. The calibration parameters usually include pipe roughness, valve settings, pipe diameter and demand. Pipe roughness, valve settings and pipe diameter are associated with the flow conditions and the demands relate to the boundary conditions. For Bangalore WDS, the values of roughness coefficient and demand are available; and the values of valve settings are not available. Hence, this value is estimated during calibration process. Dynamic Inversion (DI) nonlinear controller with Proportional Integral Derivative (PID) features (DI-PID) is used for calibrating WDS for valve settings on the basis of observed flow and roughness coefficient. From the obtained results it is observed that, controllers are capable of achieving the target flow to all the GLRs with acceptable difference between the flow meter readings and the simulated flow. After calibrating any real WDS to the field observed data, it will be useful for water authorities if the consumer demands are met up to certain extent. This can be achieved by using the concept of equitable distribution of water to different consumers. In the urban cities of developing countries, often large quantities of water are supplied to only a few consumers, leading to inequitable water supply. It is a well known fact that quantity of water supplied from the source is not distributed equitably among the consumers. Aged pipelines pump failures, improper management of water resources are some of the main reasons for it. Equitable water to different consumers can be provided by operating the system in an efficient manner. Most of the urban cities receive water from the source to intermediate reservoirs and from these reservoirs water is supplied to consumers. Therefore, to achieve equitable water supply, these two supply levels have to be controlled using different concepts/ techniques. The water requirement of each of the reservoirs has to be calculated, which may depend on the number of consumers and consumer category. Each reservoir should receive its share of water to satisfy its consumer demand and also there must be provision to accommodate shortages, if any. The calibrated model of Bangalore WDS is used to achieve equitable water supply quantity to different zones of Bangalore city. The city has large undulating terrain among different zones which leads to unequal distribution of water. Dynamic Inversion (DI) nonlinear controller with Proportional Integral Derivative (PID) features (DI-PID) is used for valve throttling to achieve the target flows to different zones/reservoirs of the city at different levels. Equitable water distribution to different reservoirs, when a part of the source fails to supply water is also discussed in this thesis. From the obtained results it is observed that, controllers were responding in all the cases in different levels of targets for such a huge network. When there is change in supply pattern to achieve the equitable supply of water to different zones, the hydraulics of the WDS will change. Therefore, it is necessary to understand whether the system is able to handle these changes. The concept of reliability can be used to analyse the performance of WDS for wide range of operating conditions. Reliability analysis of a WDS for both normal and likely to occur situations will give a better quality of service to its consumers. Calculating both hydraulic and mechanical reliability is important as the chances of occurrence of both the failure scenarios are equal in a WDS. In the present study, a methodology is presented to model the nodal, system and total reliability for water supply networks by considering the hydraulic and mechanical failure scenarios. These two reliability measures together give the total reliability of the system. Analysing a real and complex WDS for the probable chances of occurrence of the failure scenarios; and then to anlyse the total reliability of the system is not reported in the literature and this analysis is carried out in the present study for Bangalore city WDS. The hydraulics of the system for all the operating conditions is analysed using EPANET. Hydraulic reliability is calculated by varying the uncertain independent parameters (demand, roughness and source water) and mechanical reliability is calculated by assuming system component failures. The system is analysed for both the reliability scenarios by considering different chances of failure that may occur in a real WDS; and hence the total reliability is calculated by making different combinations of hydraulic and mechanical failure scenarios. Sensitivity analysis for all the zones is also carried out to understand the behavior of different demand points for large fluctuation in hydraulics of the system. From the study, it is observed that, Hydraulic reliability decreases as the demand variation increases. But, as the roughness variation increases, there is no much change in the nodal or system reliability. Consumer demand or reliability of the WDS can be increased by saving the water lost in the system. This can be achieved by tracking the water parcel from the source till the consumer end, which will give an idea about the performance of different stages and zones in achieving the target flows. Huge quantity of water is lost in WDS and hence it is necessary to account for the water lost at different levels, hence the system can be managed in a better way. In most of the intermittent water supply systems demand is controlled by supply side; there is also a need to understand the demand variation at the consumer end which in turn affects the supply. Matching this varied supply-demand gap at various levels is challenging task. To get a better control of such problem, water balance (WB) equations need to be derived at various levels. When we derive these WB equations it should be emphasized that UFW is one of the major component of this equation. Given this back ground of the complex problem, for a typical city like Bangalore, an attempt is made to derive WB equations at various levels. In the present study, stage-wise and zone-wise WB is analysed for different months based on the flow meter readings. The conceptual model developed is calibrated, validated and also the performance of the model is analysed by giving a chance of error in the flow measurement. Based on all the above observations, stage-wise and zone-wise water supply weights are also calculated. From the study it is found that, there is no much loss of water in all the four stages of supply. Water loss is minimal of about 3 % till water reaches from source to GLRs. Water is transferred between the stages during some days of the month, may be due to shortage of water or due to unexpected demand. Huge quantity of water is lost in the distribution main which is of about 40 to 45% for all the moths which is analysed. This type of model will be extremely useful for water supply managers to manage their resources more efficiently and this study is discussed in detail as a part of this thesis. As mentioned above, huge quantity of groundwater is used in urban cities and the quantity of water extracted is not accounted. In the present study, zone wise and sub zone-wise piped water and ground water used in different parts of the cities is analysed with the help of available data. From the study it is observed that, the quantity of piped water supply and UFW is consistent for the time period analysed and the quantity of water withdrawn from the borewells are varying considerably depending on the yield of the borewlls in different zones. The main components of urban water supply are piped water, ground water, rainfall and runoff generated, UFW, waste water produced and other water quantities which may be minute. In future, to manage the water resources properly, integrated water management is necessary in city scale which will give an idea about the total water produced and the water utilized at the consumer end. Therefore, integrated water management concept is carried out in Hebbal region, (a small part of Bangalore) using the available data. From the analysis we noticed that, domestic water supplied to North sub zones are better when comparing to East sub zones. This type of total water balance can be studied in other parts of Bangalore, to understand the behavior of different water components and to make better decisions. The developed model, analysis and operating conditions of this study can be applied to other similar cities like Bangalore. This type of study may be useful to water authorities for better control of the resources, or in making better decisions and these types of models will act as decision support systems.

No description available.

In the present hypercompetitive market environment of car producers established especially at the developed west european markets is very difficult to gain new customers and increase the market share. The car producing companies have to build and increase customer loyalty to ensure the sustainable growth of market share in the future. One possibility how to improve customer's loyality to brand is to provide the highest standard at both sales and service department and carefully monitor the customer satisfaction. From the satisfaction and performance indicators of the car producing company is possible to construct a mathematical model producing the market share in a given country as an output. Key indikators of customer satisfaction, sales and service and also the macroeconomical data has been used as the inputs for the model. As a target market for my analysis has been chosen Germany. This thesis presents a set of recommendations and proposals, whose implementation should ensure the improvement of the market share of the given brand on german market. The recommendation does not include only the tips for improvement of the key indicators but it also gives the overview of how to make the marketing strategy more efficient using Customer relationship management.

La quinta generación de redes móviles (5G) se encuentra a la vuelta de la esquina. Se espera provea de beneficios extraordinarios a la población y que resuelva la mayoría de los problemas de las redes 4G actuales. El éxito de 5G, cuya primera fase de estandarización ha sido completada, depende de tres pilares: comunicaciones tipo-máquina masivas, banda ancha móvil mejorada y comunicaciones ultra fiables y de baja latencia (mMTC, eMBB y URLLC, respectivamente). En esta tesis nos enfocamos en el primer pilar de 5G, mMTC, pero también proveemos una solución para lograr eMBB en escenarios de distribución masiva de contenidos. Específicamente, las principales contribuciones son en las áreas de: 1) soporte eficiente de mMTC en redes celulares; 2) acceso aleatorio para el reporte de eventos en redes inalámbricas de sensores (WSNs); y 3) cooperación para la distribución masiva de contenidos en redes celulares. En el apartado de mMTC en redes celulares, esta tesis provee un análisis profundo del desempeño del procedimiento de acceso aleatorio, que es la forma mediante la cual los dispositivos móviles acceden a la red. Estos análisis fueron inicialmente llevados a cabo por simulaciones y, posteriormente, por medio de un modelo analítico. Ambos modelos fueron desarrollados específicamente para este propósito e incluyen uno de los esquemas de control de acceso más prometedores: access class barring (ACB). Nuestro modelo es uno de los más precisos que se pueden encontrar en la literatura y el único que incorpora el esquema de ACB. Los resultados obtenidos por medio de este modelo y por simulación son claros: los accesos altamente sincronizados que ocurren en aplicaciones de mMTC pueden causar congestión severa en el canal de acceso. Por otro lado, también son claros en que esta congestión se puede prevenir con una adecuada configuración del ACB. Sin embargo, los parámetros de configuración del ACB deben ser continuamente adaptados a la intensidad de accesos para poder obtener un desempeño óptimo. En la tesis se propone una solución práctica a este problema en la forma de un esquema de configuración automática para el ACB; lo llamamos ACBC. Los resultados muestran que nuestro esquema puede lograr un desempeño muy cercano al óptimo sin importar la intensidad de los accesos. Asimismo, puede ser directamente implementado en redes celulares para soportar el tráfico mMTC, ya que ha sido diseñado teniendo en cuenta los estándares del 3GPP. Además de los análisis descritos anteriormente para redes celulares, se realiza un análisis general para aplicaciones de contadores inteligentes. Es decir, estudiamos un escenario de mMTC desde la perspectiva de las WSNs. Específicamente, desarrollamos un modelo híbrido para el análisis de desempeño y la optimización de protocolos de WSNs de acceso aleatorio y basados en cluster. Los resultados muestran la utilidad de escuchar el medio inalámbrico para minimizar el número de transmisiones y también de modificar las probabilidades de transmisión después de una colisión. En lo que respecta a eMBB, nos enfocamos en un escenario de distribución masiva de contenidos, en el que un mismo contenido es enviado de forma simultánea a un gran número de usuarios móviles. Este escenario es problemático, ya que las estaciones base de la red celular no cuentan con mecanismos eficientes de multicast o broadcast. Por lo tanto, la solución que se adopta comúnmente es la de replicar e contenido para cada uno de los usuarios que lo soliciten; está claro que esto es altamente ineficiente. Para resolver este problema, proponemos el uso de esquemas de network coding y de arquitecturas cooperativas llamadas nubes móviles. En concreto, desarrollamos un protocolo para la distribución masiva de contenidos, junto con un modelo analítico para su optimización. Los resultados demuestran que el modelo propuesto es simple y preciso, y que el protocolo puede reducir el con / La cinquena generació de xarxes mòbils (5G) es troba molt a la vora. S'espera que proveïsca de beneficis extraordinaris a la població i que resolga la majoria dels problemes de les xarxes 4G actuals. L'èxit de 5G, per a la qual ja ha sigut completada la primera fase del qual d'estandardització, depén de tres pilars: comunicacions tipus-màquina massives, banda ampla mòbil millorada, i comunicacions ultra fiables i de baixa latència (mMTC, eMBB i URLLC, respectivament, per les seues sigles en anglés). En aquesta tesi ens enfoquem en el primer pilar de 5G, mMTC, però també proveïm una solució per a aconseguir eMBB en escenaris de distribució massiva de continguts. Específicament, les principals contribucions són en les àrees de: 1) suport eficient de mMTC en xarxes cel·lulars; 2) accés aleatori per al report d'esdeveniments en xarxes sense fils de sensors (WSNs); i 3) cooperació per a la distribució massiva de continguts en xarxes cel·lulars. En l'apartat de mMTC en xarxes cel·lulars, aquesta tesi realitza una anàlisi profunda de l'acompliment del procediment d'accés aleatori, que és la forma mitjançant la qual els dispositius mòbils accedeixen a la xarxa. Aquestes anàlisis van ser inicialment dutes per mitjà de simulacions i, posteriorment, per mitjà d'un model analític. Els models van ser desenvolupats específicament per a aquest propòsit i inclouen un dels esquemes de control d'accés més prometedors: el access class barring (ACB). El nostre model és un dels més precisos que es poden trobar i l'únic que incorpora l'esquema d'ACB. Els resultats obtinguts per mitjà d'aquest model i per simulació són clars: els accessos altament sincronitzats que ocorren en aplicacions de mMTC poden causar congestió severa en el canal d'accés. D'altra banda, també són clars en què aquesta congestió es pot previndre amb una adequada configuració de l'ACB. No obstant això, els paràmetres de configuració de l'ACB han de ser contínuament adaptats a la intensitat d'accessos per a poder obtindre unes prestacions òptimes. En la tesi es proposa una solució pràctica a aquest problema en la forma d'un esquema de configuració automàtica per a l'ACB; l'anomenem ACBC. Els resultats mostren que el nostre esquema pot aconseguir un acompliment molt proper a l'òptim sense importar la intensitat dels accessos. Així mateix, pot ser directament implementat en xarxes cel·lulars per a suportar el trànsit mMTC, ja que ha sigut dissenyat tenint en compte els estàndards del 3GPP. A més de les anàlisis descrites anteriorment per a xarxes cel·lulars, es realitza una anàlisi general per a aplicacions de comptadors intel·ligents. És a dir, estudiem un escenari de mMTC des de la perspectiva de les WSNs. Específicament, desenvolupem un model híbrid per a l'anàlisi de prestacions i l'optimització de protocols de WSNs d'accés aleatori i basats en clúster. Els resultats mostren la utilitat d'escoltar el mitjà sense fil per a minimitzar el nombre de transmissions i també de modificar les probabilitats de transmissió després d'una col·lisió. Pel que fa a eMBB, ens enfoquem en un escenari de distribució massiva de continguts, en el qual un mateix contingut és enviat de forma simultània a un gran nombre d'usuaris mòbils. Aquest escenari és problemàtic, ja que les estacions base de la xarxa cel·lular no compten amb mecanismes eficients de multicast o broadcast. Per tant, la solució que s'adopta comunament és la de replicar el contingut per a cadascun dels usuaris que ho sol·liciten; és clar que això és altament ineficient. Per a resoldre aquest problema, proposem l'ús d'esquemes de network coding i d'arquitectures cooperatives anomenades núvols mòbils. En concret, desenvolupem un protocol per a realitzar la distribució massiva de continguts de forma eficient, juntament amb un model analític per a la seua optimització. Els resultats demostren que el model proposat és simple i precís / The 5th generation (5G) of mobile networks is just around the corner. It is expected to bring extraordinary benefits to the population and to solve the majority of the problems of current 4th generation (4G) systems. The success of 5G, whose first phase of standardization has concluded, relies in three pillars that correspond to its main use cases: massive machine-type communication (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable low latency communication (URLLC). This thesis mainly focuses on the first pillar of 5G: mMTC, but also provides a solution for the eMBB in massive content delivery scenarios. Specifically, its main contributions are in the areas of: 1) efficient support of mMTC in cellular networks; 2) random access (RA) event-reporting in wireless sensor networks (WSNs); and 3) cooperative massive content delivery in cellular networks. Regarding mMTC in cellular networks, this thesis provides a thorough performance analysis of the RA procedure (RAP), used by the mobile devices to switch from idle to connected mode. These analyses were first conducted by simulation and then by an analytical model; both of these were developed with this specific purpose and include one of the most promising access control schemes: the access class barring (ACB). To the best of our knowledge, this is one of the most accurate analytical models reported in the literature and the only one that incorporates the ACB scheme. Our results clearly show that the highly-synchronized accesses that occur in mMTC applications can lead to severe congestion. On the other hand, it is also clear that congestion can be prevented with an adequate configuration of the ACB scheme. However, the configuration parameters of the ACB scheme must be continuously adapted to the intensity of access attempts if an optimal performance is to be obtained. We developed a practical solution to this problem in the form of a scheme to automatically configure the ACB; we call it access class barring configuration (ACBC) scheme. The results show that our ACBC scheme leads to a near-optimal performance regardless of the intensity of access attempts. Furthermore, it can be directly implemented in 3rd Generation Partnership Project (3GPP) cellular systems to efficiently handle mMTC because it has been designed to comply with the 3GPP standards. In addition to the analyses described above for cellular networks, a general analysis for smart metering applications is performed. That is, we study an mMTC scenario from the perspective of event detection and reporting WSNs. Specifically, we provide a hybrid model for the performance analysis and optimization of cluster-based RA WSN protocols. Results showcase the utility of overhearing to minimize the number of packet transmissions, but also of the adaptation of transmission parameters after a collision occurs. Building on this, we are able to provide some guidelines that can drastically increase the performance of a wide range of RA protocols and systems in event reporting applications. Regarding eMBB, we focus on a massive content delivery scenario in which the exact same content is transmitted to a large number of mobile users simultaneously. Such a scenario may arise, for example, with video streaming services that offer a particularly popular content. This is a problematic scenario because cellular base stations have no efficient multicast or broadcast mechanisms. Hence, the traditional solution is to replicate the content for each requesting user, which is highly inefficient. To solve this problem, we propose the use of network coding (NC) schemes in combination with cooperative architectures named mobile clouds (MCs). Specifically, we develop a protocol for efficient massive content delivery, along with the analytical model for its optimization. Results show the proposed model is simple and accurate, and the protocol can lead to energy savings of up to 37 percent when compared to the traditional approach. / Leyva Mayorga, I. (2018). On reliable and energy efficient massive wireless communications: the road to 5G [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/115484 / TESIS

<div> This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks.</div><div><br></div><div> The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model.</div><div><br></div><div> The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. </div><div><br></div><div> Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.</div>