This thesis examines how an econometric model, which allows for simultaneity, performs when estimating electricity supply and demand on the Swedish aggregated electricity market, divided into its four price areas. Previous research and theory points to the importance of taking simultaneity into consideration when estimating simultaneous equation models. The purpose of the thesis is to clarify whether a simultaneous equation model is adequate for estimation of the Swedish electricity market. To answer the question, the existence of simultaneity between electricity price and quantity (produced and consumed electricity) is examined. Regression analyses are performed for each price area and the coefficients are estimated with 2SLS, while Hausman tests and F-tests are carried out to unveil potential simultaneity. The results show that the performance of the model of the thesis varies: the coefficients of the price variables in the demand functions are never statistically significant, while the coefficients of the monthly dummy variables in most cases have expected signs and are statistically significant, especially during summer. Regarding the supply side, the results show that net export have the expected positive statistically significant effect on quantity of electricity supplied in price areas 2, 3, and 4, while the signs and significance of the coefficients of the price variables varies. A price increase in area 3 has a statistically significant positive effect on supply in all areas, while the price of area 4 has a statistically significant negative effect on supply in area 3 and 4. A price increase in area 1 leads to a statistically significant positive effect on supply only in area 2, while such a change in the price of area 2 is associated with a statistically significant decrease of the supply in that same area. As to simultaneity between price and quantity demanded, the Hausman tests gives sufficient evidence to conclude that simultaneity exists in all price areas. Similarly, on the supply side the performed F-tests result in clear evidence of existence of simultaneity. / Denna uppsats undersöker hur en ekonometrisk modell som tar hänsyn till simultanitet presterar vid estimering av utbjuden och efterfrågad kvantitet av elektricitet på den svenska aggregerade elmarknaden, uppdelad efter de fyra elområdena. Tidigare forskning och teori visar på betydelsen av att ta simultanitet i beaktning när simultana ekvationsmodeller estimeras. Uppsatsen syftar till att klarlägga om en simultan ekvationsmodell är lämplig för estimering av den svenska elmarknaden. För att få svar på frågan undersöks om det förekommer simultanitet mellan elpris och kvantitet (producerad och konsumerad el). Regressionsanalyser utförs för varje elområde och koefficienterna skattas med hjälp av 2SLS, medan Hausmantest och F-test utförs för att upptäcka eventuell simultanitet. Uppsatsens modell levererar varierande resultat: i efterfrågeekvationerna är prisvariabeln aldrig statistiskt signifikant medan månadsvariablerna i de flesta fall har förväntat tecken och är statistiskt signifikanta, framför allt under sommarhalvåret. För utbudssidan visar resultatet att nettoexport har väntad positiv statistiskt signifikant effekt på utbjuden kvantitet i elområde 2, 3 och 4, medan tecken och signifikans för prisvariablernas koefficienter varierar. En ökning av priset i område 3 leder till en statistiskt signifikant utbudsökning i alla områden, medan priset i område 4 har en statistiskt signifikant negativ effekt på utbudet i område 3 och 4. En prisökning i elområde 1 leder endast till en statistiskt signifikant positiv utbudsökning i område 2, medan en prisökning i elområde 2 i stället endast leder till en statistiskt signifikant utbudsminskning i samma område. Vad gäller simultanitet mellan pris och kvantitet på efterfrågesidan visar Hausmantesten att det finns tillräckligt starka statistiska bevis för att påstå att simultanitet förekommer i alla elområden. Även för utbudssidan resulterar de utförda F-testen i tydliga bevis för förekomst av simultanitet.

Studien ämnar att tillgängliggöra kunskap om svenska hushålls konsumtionsbeteenden i en ekonomiskt svår tid; en tid präglad av hög inflation och höga elpriser. Kunskap och förståelse för svenska hushålls konsumtionsbeteenden är en avgörande faktor för att Sverige ska nå uppställda klimatmål – genom träffsäkra policyer och utveckling av klimatsmarta verktyg.   Genom en litteraturstudie, enkätundersökning samt semi-strukturerade intervjuer har detta utretts och av detta framgår att majoriteten av svenska hushåll har minskat sin elkonsumtion utan att uppfatta att denna förändring har en stor påverkan på livskvalitet. Det framgår även att 59% hushåll som minskat sin elkonsumtion inte uppskattar att deras elkonsumtion kommer att återgå till högre nivåer i det fall då priserna sjunker. Det kartläggs även att det bland svenska hushåll råder en hög kunskapsnivå som är en avgörande faktor för att medvetenheten även ska mynna ut i träffsäkra energieffektiviserings- och besparingsåtgärder. / This study aims to increase knowledge about the electricity consumption patterns observed in Swedish households during economically challenging times, characterised by inflation and high electricity prices. Knowledge and understanding of Swedish households' consumption patterns is a crucial factor in increasing Sweden’s ability to reach set climate goals – through accurate policies and through development of climate-smart tools.  Through a literature study, a survey, and semi-structured interviews, this has been investigated and it appears that a majority of Swedish households have reduced their electricity consumption without perceiving their applied changes as having a major impact on their quality of life. It is also observed that 59% of the households that have reduced their electricity consumption do not estimate that their electricity consumption will return to higher levels in the event that electricity prices were to decrease. This study also shows that there is a high level of knowledge among Swedish households, which is a decisive factor for the awareness to also result in accurate energy efficiency and saving measures.

This master thesis evaluates the incentives of a newly implemented market controlled network tariff by analyzing consumption data and constructing a time-differentiated debiting model. The tariff was implemented by Sandviken Energi Elnät AB and the thesis evaluates its customers consumption data compared to data provided by Sundsvall Elnät AB. The differences in data is evaluated by statistical tests of Students t-test, Bayesian t-test and χ2-test with the result that no statistically significant change in user pattern can be found and thus an elucidation of the incentives must be made in the form of a hourly time-differentiated debating model. The thesis also evaluates the cost incentives of the model compared to spot prices where it is shown that the tariff model can benefit much from the spot prices hourly incentives in its hourly time-differentiated model. Five time-differentiated models were constructed and presented where three uses a color coding scheme. The conclusion is that a color coded time-differentiated tariff should give the costumers clear and cost-effective incentives.

Les modèles de mélange pour la régression sont utilisés pour modéliser la relation entre la réponse et les prédicteurs, pour des données issues de différentes sous-populations. Dans cette thèse, on étudie des prédicteurs de grande dimension et une réponse de grande dimension. Tout d’abord, on obtient une inégalité oracle ℓ1 satisfaite par l’estimateur du Lasso. On s’intéresse à cet estimateur pour ses propriétés de régularisation ℓ1. On propose aussi deux procédures pour pallier ce problème de classification en grande dimension. La première procédure utilise l’estimateur du maximum de vraisemblance pour estimer la densité conditionnelle inconnue, en se restreignant aux variables actives sélectionnées par un estimateur de type Lasso. La seconde procédure considère la sélection de variables et la réduction de rang pour diminuer la dimension. Pour chaque procédure, on obtient une inégalité oracle, qui explicite la pénalité nécessaire pour sélectionner un modèle proche de l’oracle. On étend ces procédures au cas des données fonctionnelles, où les prédicteurs et la réponse peuvent être des fonctions. Dans ce but, on utilise une approche par ondelettes. Pour chaque procédure, on fournit des algorithmes, et on applique et évalue nos méthodes sur des simulations et des données réelles. En particulier, on illustre la première méthode par des données de consommation électrique. / Finite mixture regression models are useful for modeling the relationship between a response and predictors, arising from different subpopulations. In this thesis, we focus on high-dimensional predictors and a high-dimensional response. First of all, we provide an ℓ1-oracle inequality satisfied by the Lasso estimator. We focus on this estimator for its ℓ1-regularization properties rather than for the variable selection procedure. We also propose two procedures to deal with this issue. The first procedure leads to estimate the unknown conditional mixture density by a maximum likelihood estimator, restricted to the relevant variables selected by an ℓ1-penalized maximum likelihood estimator. The second procedure considers jointly predictor selection and rank reduction for obtaining lower-dimensional approximations of parameters matrices. For each procedure, we get an oracle inequality, which derives the penalty shape of the criterion, depending on the complexity of the random model collection. We extend these procedures to the functional case, where predictors and responses are functions. For this purpose, we use a wavelet-based approach. For each situation, we provide algorithms, apply and evaluate our methods both on simulations and real datasets. In particular, we illustrate the first procedure on an electricity load consumption dataset.

L’objectif de cette thèse est d’étudier les nouvelles dynamiques et leurs impacts dans le secteur de l'électricité. Elle discute des sujets critiques d’après les perspectives de la macroéconomie, de la configuration structurelle, et de la transition vers des sources d'énergie renouvelables. Plus précisément, trois sujets se dégagent: le lien entre la consommation d'électricité et la croissance économique, les impacts de l'intégration verticale entre les producteurs et les détaillants, et les impacts d'intégration de production d'énergie renouvelable intermittente. En mettant en jeu ces trois sujets, elle tente d’apporter des réponses aux défis principaux de la sécurité d'approvisionnement, de la compétitivité, et de la durabilité du développement énergétique. En donnant de nouvelles orientations dans la recherche sur l’économie de l’énergie, elle servira à éclairer des débats politiques. / The objective of this thesis is to study the new dynamics and their impacts in the electricity sector. It discusses the critical issues from the perspectives of macroeconomics, structural configuration, and a transition to renewable energy sources. More precisely, three topics emerge: the nexus between electricity consumption and economic growth, the impacts of vertical integration between power generators and retailers, and the market impacts and integration issues of intermittent renewable generation. By studying these three topics, it provides answers to the key challenges of supply security, competitiveness and sustainable development in the energy sector. By giving new research directions of energy economics, it serves to inspire related policy debates.

Dans un contexte où les tensions liées aux ressources énergétiques fossiles sont de plus en plus vives, concevoir une nouvelle manière d'appréhender le contexte énergétique est devenu essentiel. Les moyens de production et de consommation énergétiques habituels ont montré leur limite avec l'apparition de nouveau type de pollution pour différents secteurs. Dans ce rapport de thèse, nous nous sommes essentiellement axés sur le secteur de l'électricité en proposant un outil, d'aide à la décision, pour simuler la consommation électrique ainsi que la production électrique à partir des énergies renouvelables (EnR). La simulation de la consommation électrique permet d'avoir des informations à différents échelles d'observation en s'appuyant sur une démarche systémique et typologique, qui permet de calculer le bilan carbone associé à cette consommation ainsi que son coût annuel. Par la suite, cette consommation a été analysée à l'échelle horaire afin de pouvoir là mettre en relation avec des fichiers de production pour effectuer un pilotage au niveau de la courbe de charge. Ce pilotage a pour but de lisser les pics au niveau de la courbe de charge. Les premiers résultats analytiques obtenus à l'aide des outils développés montrent qu'il est possible de réduire l'appel au réseau électrique normal à un certain niveau en fonction des dimensionnements des systèmes de production EnR et du stockage. Ainsi que de pouvoir limité les coûts d'investissement au juste nécessaire, c'est-à-dire avoir un prix le moins cher possible, grâce à une optimisation du système EnR. / In a context where the tensions linked to fossil energy resources are increasing, design a new way of understanding the energy context has become essential. The usual means of energy production and consumption have shown their limit with the appearance of new types of pollution for different sectors. In this thesis, we mainly focused on the electricity sector by proposing a tool to simulate electricity consumption and electricity production from renewable energies (RES). Simulation of electricity consumption allows having information on different observation scales based on a systemic and typological approach, according to which the associated carbon footprint to this consumption is being calculated as well as its annual cost. Subsequently, this consumption was analyzed at the hourly scale, which is to relate it to the production files in order to control the load curve. This control aims to smooth down the peaks of the load curve. The first analytical results, obtained by using the developed tools, show that it is possible to reduce the use of the normal electrical network to a certain level according to the dimensions of the RES production systems and storage.

本文有兩個研究目標，第一個是比較政大用電量與氣溫之間的相關性，第二則是分析影響黃金價格波動的因素。本文使用到的研究方法有希爾柏特黃轉換（HHT）與一些統計值。 　　本研究使用的分析數據如下：政大逐時用電量、台北逐時氣溫以及倫敦金屬交易所（London Metal Exchange）的月平均黃金價格。透過經驗模態分解法（EMD），我們可以將分析數據拆解成數個互相獨立的分量，再藉由統計值選出較重要的分量並分析其意義。逐時用電量的重要分量為日分量、週分量與趨勢；逐時氣溫的重要分量為日分量與趨勢；月平均黃金價格的重要分量則是低頻分量與趨勢。 藉由這些重要分量，我們可以更加了解原始數據震盪的特性，並且選出合理的平均週期將所有的分量分組，做更進一步的分析。逐時用電量與逐時氣溫分成高頻、中頻、低頻與趨勢四組，其中低頻與趨勢相加的組合具有最高的相關性。月平均黃金價格則是分為高頻、低頻與趨勢三組，其中高頻表現出供需以及突發事件等短週期因素，低頻與歷史上對經濟有重大影響的事件相對應，趨勢則是反應出通貨膨脹的現象。 / There are two main separated researched purposes in this thesis. First one is comparing the correlation between electricity consumption and temperature in NCCU. Another one is analyzing the properties of gold price volatility. The methods used in the study are Hilbert-Huang transform (HHT) and some statistical measures. 　　The following original data: hourly electricity consumption in NCCU, hourly temperature in Taipei, and the LME monthly gold prices are decomposed into several components by empirical mode decomposition (EMD). We can ascertain the significant components and analyze their meanings or properties by statistical measures. The significant components of each data are shown as follows: daily component, weekly component and residue for hourly electricity consumption; daily component and residue for hourly temperature; low frequency components and residue for the LME monthly gold prices. 　　We can understand more properties about these data according to the significant components, and dividing the components into several terms based on reasonable mean period. The components of hourly electricity consumption and hourly temperature are divided into high, mid, low frequency terms and trends, and the composition of low frequency terms and trends have the highest correlation between them. The components of LME monthly gold prices are divided into high, low frequency term and trend. High frequency term reveals the supply-demand and abrupt events. The low frequency term represents the significant events affecting economy seriously, and trend shows the inflation in the long run.

Energimyndigheten har drivit ett projekt kallat ”Förbättrad energistatistik i bebyggelsen” för att få mer kunskap om energianvändningen i byggnader.  Denna rapport fokuserar på ”Mätning av hushållsel på apparatnivå” som var ett delprojekt. Diverse regressionsmodeller används i denna rapport för att undersöka sambandet mellan elanvändningen och de olika förklarande variablerna, som exempelvis hushållens bakgrundsvariabler, hushållstyp och geografiska läge, elförbrukningen av olika elapparater samt antalet elapparater. Datamaterialet innefattar 389 hushåll där de flesta är spridda runt om i Mälardalen. Ett fåtal mätningar gjordes på hushåll i Kiruna och Malmö. Slutsatsen vi kan dra från denna uppsats är att hushållens bakgrund, hustyp, geografiska läge och antal elapparater samt dessa apparaters typ har relevans för elförbrukningen i ett hushåll. / The Swedish Energy Agency conducted a project which is called “Improved energy statistics for settlements”. This report focuses on one field of the project: “households’ electricity use on device level”. Various regression models are used in the analysis to analyze the relationship between electricity usage and different explanatory variables, for instance: background variables for the household, type of household, geographical setting, usage of different electrical devices and quantity of electrical devices used.  The data material consists of 389 households which are spread around the region of Märlardalen except for a few households from the communities of Kiruna and Malmö. The conclusion we can draw from this thesis shows that the background variables for a household, its type, its geographical setting and the amount and type of devices it contains all have a contribution to the electricity usage in the household. / Förbättrad energistatistik i bebyggelsen

Through theory and econometric instrumentals, this work intends to estimate the behavior of Electric Energy’s Demand Curve to Brazil, through the behavior of important variables for residential sector, industrial and commercial sectors. It’s important to achievement for futures projections that enable to know if installed capacity is enough to answer Energy demand. Using Co-integration concept, were estimated the Vector Error Correction, used to project the demand to the period of 2009-2017. There were some obstacles regarding the estimation of the curve of the industrial sector with respect to the variable IPA-OG industrial machinery and equipment and IPA-OG fuels and lubricants, where their estimated coefficients were inconclusive. Energy consumption by the residential sector is showing increasing but at a decreasing rate, and was influenced by the efficiency of consumption (consumer behavior on the part of the post-rationing and the use of more efficient equipment for the use of electricity). As results, the Energy’s demand is growing and may be superior to installed capacity. Was introduced the Social Cost Politic concept to Energy’s demand and the results show that it politics can reduce the demand, and it can be used as a restrictive measure to Energy’s demand, rather than aggressive restrictive politics. / Com base em subsídios teóricos e no instrumental econométrico, este trabalho pretende estimar o comportamento da Curva de Demanda por energia elétrica para o Brasil, considerando o comportamento de variáveis relevante aos setores residencial, comercial e industrial. A estimação da curva de demanda propicia um instrumental que permite a realização de projeções futuras, as quais por sua vez, permitem verificar se a capacidade instalada de energia atende adequadamente a expectativa de demanda por este produto. Pelo conceito de Co-integração, foram estimados os Modelos de Correção de Erros (VEC), utilizado para projetar o consumo para o período de 2009-2017. De forma geral, os resultados alcançados foram bons, não tendo coeficientes não significativos e sendo os sinais dos parâmetros concernentes à teoria econômica. Houve alguns entraves quanto à estimação da curva do setor industrial com relação à variável IPA-OG máquinas e equipamentos industriais e IPA-OG combustíveis e lubrificantes, onde seus coeficientes estimados foram inconclusivos. Utilizou-se, pois, novas proxies para tais variáveis, a saber, câmbio real efetivo e preço médio – óleo combustível. Através dos resultados alcançados, o consumo crescente de energia pode ser superior a capacidade de fornecimento de energia, evidenciando a necessidade de implantação de políticas restritivas ao consumo de energia. O consumo de energia por parte do setor residencial se mostra crescente, mas a uma taxa decrescente, sendo influenciado pela maior eficiência do consumo (comportamento por parte do consumidor pós-racionamento e utilização de equipamentos mais eficientes quanto ao uso da energia elétrica). Buscou-se introduzir o conceito de Custo Social ao consumo de energia e os resultados mostram que dentre os setores, o industrial sofrera maior penalidade no consumo e que tal política pode proporcionar redução no consumo, podendo ser esta política utilizada como medida restritiva para a demanda por energia.

Made available in DSpace on 2010-04-20T20:51:44Z (GMT). No. of bitstreams: 0 Previous issue date: 2006-03-10T00:00:00Z / Esta pesquisa teve como principal objetivo examinar a relação entre Consumo de Energia Elétrica e Renda Familiar nos domicílios do município de São Paulo. Investigou-se a utilidade do consumo de energia elétrica como base para um indicador que possibilite a extensão e o refinamento do Critério de Classificação Econômica Brasil para estimar o poder de compra da população em geral. A pesquisa dividiu-se em dois níveis de investigação. O primeiro, domiciliar, para o qual foram utilizados três conjuntos de dados oriundos de pesquisas domiciliares (Pesquisa ABRADEE, Pesquisa de Posses e Hábitos do PROCEL, e Pesquisa de Microcrédito da Baixa Renda da FGV-EAESP). O segundo nível, territorial, investigou indicadores de renda, consumo de energia elétrica e classe econômica agregados por áreas de ponderação (conjunto de setores censitários), e utilizou microdados do Censo Demográfico 2000 do município de São Paulo em conjunto com a base de domicílios da AES Eletropaulo. A investigação domiciliar mostrou que não há vantagens na substituição plena da aplicação do Critério Brasil pela coleta de indicadores de consumo de energia elétrica em levantamentos domiciliares. No entanto, o uso combinado do Critério Brasil, do valor da conta de luz e do número de pessoas (ou número de dormitórios) no domicílio apresenta benefícios na classificação da renda (os gráficos de ganhos das árvores de classificação combinadas aproximam-se mais da distribuição real da renda, apesar de o coeficiente de explicação da renda aumentar apenas de 0,577 para 0,582). Além disso, ao contrário do que se especulava, para a baixa renda a associação entre renda e consumo de energia elétrica mostrou-se fraca, apesar de o coeficiente de explicação da renda aumentar de 0,222 para 0,300 quando incorporamos o consumo de energia elétrica e o número de pessoas ao modelo de regressão da renda pelo Critério Brasil. Em nível territorial, as relações entre Renda, Consumo de Energia Elétrica e Classificação Econômica do Critério Brasil mostraram-se muito fortes (os coeficientes de explicação da renda atingiram valores de 0,912 a 0,960), permitindo que medidas de consumo médio de energia elétrica agregadas em áreas de ponderação sejam ótimos indicadores regionais de concentração de renda e classificação econômica dos domicílios para o município de São Paulo. Por serem atuais, disponíveis e de atualização mensal, os indicadores de consumo de energia elétrica, quando disponibilizados pelas empresas de distribuição de energia, podem ser de grande utilidade para empresas de mercado, como subsídio a estratégias que necessitem de informações de classificação, concentração e previsão da renda domiciliar. / The main research objective was to analyze the relationship between household Electricity Consumption and Family Income in the city of São Paulo in order to evaluate the potential benefits of adding electricity consumption to the Brazilian Economic Classification Criteria, an index frequently used to estimate a family’s purchasing power. To achieve these goals, statistical models were developed at two different levels of aggregation. The first and most disaggregated level was the household, for which data from three different research studies were combined (ABRADEE Research, PROCEL Possessions and Habits Research, and Microcredit for Low Income Families Research by FGV-EAESP). The second level (the territorial one), with household aggregated at the level of weighted areas (set of census tracts), used income indicators, electric energy consumption and economic classification data from the Demographic Census 2000 of the city of São Paulo and the AES Eletropaulo household databases. The results in household investigation show that energy consumption alone cannot substitute for Brazilian Criteria. However, the combined use of the Brazilian Criteria, the household electricity monthly bill and the number of residents (or number of bedrooms) in the household significantly improves household income estimates, as shown by the results of classification tress model, in which the resulting predicted distribution curve better approximates the real distribution, although coefficient of determination R-squared grows from only 0,577 to 0,582. However, contrary to a priori expectation, among low income household, the level of association between income and electricity consumption was very weak. Nevertheless, household income forecast can be enhanced, with an improvement of the model’s R-squared from 0,222 to 0,300 when the electricity bill and the number of resident are included in a regression model of household income against the Brazilian Criteria. At the weighted area level, the relationship between Income, Electricity Consumption and Brazilian Criteria’s Economic Classification are very strong, with coefficients of determination R-squared ranging from 0,912 to 0,960. This results supports the use of the mean household electricity consumption, at a territorial aggregated level, as an excellent regional indicator of income concentration in the city of São Paulo. As it is an easily available and monthly update information, the electric energy consumption indicators, if made available by energy distribution companies, will be useful for strategy formulation and decision making for which household income classification data are critical.