La Previsione dei Consumi Elettrici nel Mercato Energetico Italiano : un nuovo modello empirico con struttura triangolare

L'obiettivo principale della tesi è lo sviluppo di un modello empirico previsivo di breve periodo che sia in grado di offrire previsioni precise ed affidabili dei consumi di energia elettrica su base oraria del mercato italiano. Questo modello riassume le conoscenze acquisite e l'esperienza fatta durante la mia attuale attività lavorativa presso il Romagna Energia S.C.p.A., uno dei maggiori player italiani del mercato energetico. Durante l'ultimo ventennio vi sono stati drastici cambiamenti alla struttura del mercato elettrico in tutto il mondo. Nella maggior parte dei paesi industrializzati il settore dell'energia elettrica ha modificato la sua originale conformazione di monopolio in mercato competitivo liberalizzato, dove i consumatori hanno la libertà di scegliere il proprio fornitore. La modellazione e la previsione della serie storica dei consumi di energia elettrica hanno quindi assunto un ruolo molto importante nel mercato, sia per i policy makers che per gli operatori. Basandosi sulla letteratura già esistente, sfruttando le conoscenze acquisite 'sul campo' ed alcune intuizioni, si è analizzata e sviluppata una struttura modellistica di tipo triangolare, del tutto innovativa in questo ambito di ricerca, suggerita proprio dal meccanismo fisico attraverso il quale l'energia elettrica viene prodotta e consumata nell'arco delle 24 ore. Questo schema triangolare può essere visto come un particolare modello VARMA e possiede una duplice utilità, dal punto di vista interpretativo del fenomeno da una parte, e previsivo dall'altra. Vengono inoltre introdotti nuovi leading indicators legati a fattori meteorologici, con l'intento di migliorare le performance previsive dello stesso. Utilizzando quindi la serie storica dei consumi di energia elettrica italiana, dall'1 Marzo 2010 al 30 Marzo 2012, sono stati stimati i parametri del modello dello schema previsivo proposto e valutati i risultati previsivi per il periodo dall'1 Aprile 2012 al 30 Aprile 2012, confrontandoli con quelli forniti da fonti ufficiali.

Integrating structured and unstructured data in a business-intelligence-system

The recent liberalization of the German energy market has forced the energy industry to develop and install new information systems to support agents on the energy trading floors in their analytical tasks. Besides classical approaches of building a data warehouse giving insight into the time series to understand market and pricing mechanisms, it is crucial to provide a variety of external data from the web. Weather information as well as political news or market rumors are relevant to give the appropriate interpretation to the variables of a volatile energy market. Starting from a multidimensional data model and a collection of buy and sell transactions a data warehouse is built that gives analytical support to the agents. Following the idea of web farming we harvest the web, match the external information sources after a filtering and evaluation process to the data warehouse objects, and present this qualified information on a user interface where market values are correlated with those external sources over the time axis.

Efficiency in Deregulated Electricity Markets: Offer Cost Minimization vs. Payment Cost Minimization Auction

This study of the wholesale electricity market compares the efficiency performance of the auction mechanism currently in place in U.S. markets with the performance of a proposed mechanism. The analysis highlights the importance of considering strategic behavior when comparing different institutional systems. We find that in concentrated markets, neither auction mechanism can guarantee an efficient allocation. The advantage of the current mechanism increases with increased price competition if market demand is perfectly inelastic. However, if market demand has some responsiveness to price, the superiority of the current auction with respect to efficiency is not that obvious. We present a case where the proposed auction outperforms the current mechanism on efficiency even if all offers reflect true production costs. We also find that a market designer might face a choice problem with a tradeoff between lower electricity cost and production efficiency. Some implications for social welfare are discussed as well.

Análisis de los mercados de gas mayoristas en Europa: Francia, Reino Unido, Bélgica y Holanda

Este proyecto consiste en una previa investigación descriptiva del mercado mayorista de gas en España. Para ello, se ha estudiado en profundidad el funcionamiento de los componentes que constituyen este sistema y las herramientas necesarias utilizadas para el sostenimiento del mismo. Se ha analizado las capacidades, peajes, etc. para poder extrapolar estos conocimientos al resto de los mercados europeos examinados. Una vez explorado el mercado español, se ha analizado el mercado belga, francés, inglés y holandés. En estos mercados se ha hecho un estudio de las bases necesarias que un comercializador necesita para poder introducirse en estos nuevos mercados. Por último, al tratarse de un proyecto de investigación, se ha realizado un estudio del coste económico que un estudio como este podría conllevar. 3 ABSTRACT This project is a descriptive pre-research study of the wholesale gas market in Spain. For that purpose, the system's structure, functioning and the strategies required for its sustainability have been studied extensively. Capacities, tolls, etc. have been analysed so that results can be then extrapolated to the other markets examined. Once the spanish market was explored; belgian, french, english and dutch markets were analysed. In these markets, the basis required for a potential marketer entering these markets, have been evaluated. At last, as a research study, it includes an economic cost analysis that a study like this would imply

A dynamic factor model for mid-term forecasting of wind power generation

The main objective of this paper is the development and application of multivariate time series models for forecasting aggregated wind power production in a country or region. Nowadays, in Spain, Denmark or Germany there is an increasing penetration of this kind of renewable energy, somehow to reduce energy dependence on the exterior, but always linked with the increaseand uncertainty affecting the prices of fossil fuels. The disposal of accurate predictions of wind power generation is a crucial task both for the System Operator as well as for all the agents of the Market. However, the vast majority of works rarely onsider forecasting horizons longer than 48 hours, although they are of interest for the system planning and operation. In this paper we use Dynamic Factor Analysis, adapting and modifying it conveniently, to reach our aim: the computation of accurate forecasts for the aggregated wind power production in a country for a forecasting horizon as long as possible, particularly up to 60 days (2 months). We illustrate this methodology and the results obtained for real data in the leading country in wind power production: Denmark

Integrated plant monitoring to improve plant operation strategy and results

The more and more demanding conditions in the power generation sector requires to apply all the available technologies to optimize processes and reduce costs. An integrated asset management strategy, combining technical analysis and operation and maintenance management can help to improve plant performance, flexibility and reliability. In order to deploy such a model it is necessary to combine plant data and specific equipment condition information, with different systems devoted to analyze performance and equipment condition, and take advantage of the results to support operation and maintenance decisions. This model that has been dealt in certain detail for electricity transmission and distribution networks, is not yet broadly extended in the power generation sector, as proposed in this study for the case of a combined power plant. Its application would turn in direct benefit for the operation and maintenance and for the interaction to the energy market

A integração da indústria de energia elétrica na América do Sul: análise dos modelos técnicos e de regulamentação.

Os recursos energéticos naturais não estão distribuídos uniformemente pelo globo terrestre, e são raros os países que os têm na quantidade e na qualidade que necessitam para atender as suas necessidades. Ante a essa realidade, o comércio de energéticos tem sido a forma principal de acesso dos países que não os dispõem em relação as suas necessidades. Esse comércio, que muitas vezes é regido por tratados ou acordos firmados entre países ou blocos econômicos regionais, diversificou-se, traspassou fronteiras e, atualmente, tornou-se um item significativo nas pautas de exportações de vários países. A evolução desse comércio tem a favor a alternativa de integração por meio de interconexões estratégicas de redes e da constituição de mercados comuns, que viabilizam a exploração do potencial de complementariedade energética de forma mais racional. Diante desse contexto, esta dissertação apresenta um estudo exploratório que avalia o estado da arte da integração energética sul-americana e faz análises dos modelos técnicos, das regulamentações, das regulações regionais e multilaterais estabelecidas pelos blocos econômicos sul-americanos e pela Organização Mundial do Comércio. De forma complementar, o estudo verifica e apresenta os fatores que podem comprometer o avanço e a instituição de um futuro mercado comum de energia no continente, conclui pela viabilidade do prosseguimento de ações em prol da ampliação da integração da indústria de energia elétrica na América do Sul e tece recomendações. Os resultados e as recomendações deste trabalho oferecem um embasamento procedimental para a gestão e a atuação institucional dos envolvidos no processo de integração energética da indústria de energia elétrica da região sul americana.

Formação do preço da energia convencional nas transações entre agentes no mercado de curto prazo brasileiro.

Hoje no mercado brasileiro de eletricidade, o preço da energia convencional é composto pela soma do valor do Preço de Liquidação das Diferenças (PLD) divulgado pela Câmara de Comercialização de Energia Elétrica (CCEE) semanalmente com o valor do Spread negociado bilateralmente no mercado à vista (mercado de curto prazo), resultante do equilíbrio entre oferta e demanda. Em alguns momentos, o valor do Spread chega a representar mais de 100% do custo total da energia. Este trabalho faz uma análise do mercado brasileiro, bem como, de alguns mercados no exterior de energia elétrica e destaca os pontos que tem influência direta, na formação do Spread da energia convencional e como isso afeta a decisão de contratação dos agentes. Além disso, o trabalho busca encontrar correlações entre dados divulgados, como carga e oferta de energia, com o ágio negociado no mercado de curto prazo, buscando entender o real impacto de cada um desses fatores e explicar as grandes variações já observadas. Sugere-se também um modelo de regressão linear múltipla para a projeção de valores do ágio. Para tanto, foram utilizadas informações proveniente de um banco de dados de cotações de negócios efetivamente realizados no curto prazo desde janeiro de 2011 até julho de 2014, bem como informações retiradas da CCEE e Operador Nacional do Sistema (ONS).

Abolishing Oil Indexation in Gas Contracts: Is it the cure-all? CEPS Commentaries, 3 March 2014

Recently, the EU energy debate has been dominated by the discussion on energy prices and the competitiveness of the European industry. According to the latest estimates of the International Energy Agency, gas prices in the US are one-quarter of those in Europe. Moreover, prices of imported gas vary across the EU member states. Some EU policy-makers hope that the completion of the internal energy market and the transition to hub-based pricing will solve these discrepancies. Julian Wieczorkiewicz asks in this Commentary whether the abolition of oil-indexation will constitute a cure-all for the above-mentioned problems.

German companies strengthen their cooperation with Russian gas suppliers. OSW Commentary No. 64, 2011-10-24

Germany’s decision to give up the use of nuclear energy will force it to find a conventional low-carbon energy source as a replacement; in the short term, in addition to coal, this is likely to be gas. Due to their continued high debt and the losses associated with the end of atomic power, German companies will not be able to spend large funds on investing in conventional energy. First of all, they will aim to raise capital and repay their debts. The money for this will come from selling off their less profitable assets; this will include sales on the gas market. This will create opportunities for natural gas exporters and extraction companies such as Gazprom to buy back some of the German companies’ assets (electricity companies, for example). The German companies will probably continue to seek to recover the costs incurred in the investment projects already underway, such as Nord Stream, the importance of which will grow after Russian gas imports increase. At the same time, because of their debts, the German companies will seek to minimise their investment costs by selling some shares on the conventional energy market, to Russian corporations among others; the latter would thus be able to increase their stake in the gas market in both Western (Germany, Great Britain, the Benelux countries) and Central Europe (Poland, the Czech Republic). It is possible that while establishing the details of cooperation between the Russian and German companies, Russia will try to put pressure on Germany to give up competing projects such as Nabucco. However, a well-diversified German energy market should be able to defend itself against attempts to increase German dependence on Russian gas supplies and the dictates of high prices.

Energising the TTIP: Political economy of the trade policy rationale. Paper No. 9 in the CEPS-CTR project “TTIP in the Balance’’and CEPS Special Report No. 113/July 2015

Despite accounting for a significant share of global trade and the resulting interdependencies from it, energy governance remains largely fragmented and there is no global framework or agreement defining the rules of energy trade. This paper, after presenting the main global and regional energy market developments, discusses the opportunities to ‘energise the TTIP’, i.e. to include a chapter dedicated to trade and cooperation in the sphere of energy. The shale revolution in the US, the ever-rising interconnectedness of energy markets (recently proven by the disappearance of the ‘Asian gas premium’) and the EU’s quest to diversify its energy supplies generally sets favourable conditions to reinforce energy relations between the EU and the US. The question, as is often the case, is whether there is sufficient political will to tighten relations in a strategic sphere with connotations for national security and sovereignty.

Rethinking the security of the European Union’s gas supply. Bruegel Policy Contribution, Issue 2016/01 January 2016

Highlights: • The security of the European Union’s gas supplies is crucial to ensuring that supplies to households are not disrupted in freezing winters, that industry can flourish and that the EU cannot be blackmailed in vital foreign policy questions. • Gas supply security should be addressed at EU level because a joint solution would be cheaper, national approaches could undermine the internal energy market and have adverse effects on other countries, and the EU Treaty explicitly calls for energy solidarity. • The current focus on supply diversification and reduction of dependence on imported gas is expensive and does not constitute a systemic response. • Instead of doing everything to reduce gas supplies from key suppliers, gas supply security could more effectively be safeguarded by ensuring that unused alternatives are maintained so that they can be tapped into for an indefinite period in case of supply disruption from a key supplier.This Policy Contribution outlines a market approach that could safeguard gas supply security at very low cost.

Variational inference for Student-t MLP models

This paper presents a novel methodology to infer parameters of probabilistic models whose output noise is a Student-t distribution. The method is an extension of earlier work for models that are linear in parameters to nonlinear multi-layer perceptrons (MLPs). We used an EM algorithm combined with variational approximation, the evidence procedure, and an optimisation algorithm. The technique was tested on two regression applications. The first one is a synthetic dataset and the second is gas forward contract prices data from the UK energy market. The results showed that forecasting accuracy is significantly improved by using Student-t noise models.

Developing a decision framework for the strategic sourcing of biomass

The deployment of bioenergy technologies is a key part of UK and European renewable energy policy. A key barrier to the deployment of bioenergy technologies is the management of biomass supply chains including the evaluation of suppliers and the contracting of biomass. In the undeveloped biomass for energy market buyers of biomass are faced with three major challenges during the development of new bioenergy projects. What characteristics will a certain supply of biomass have, how to evaluate biomass suppliers and which suppliers to contract with in order to provide a portfolio of suppliers that best satisfies the needs of the project and its stakeholder group whilst also satisfying crisp and non-crisp technological constraints. The problem description is taken from the situation faced by the industrial partner in this research, Express Energy Ltd. This research tackles these three areas separately then combines them to form a decision framework to assist biomass buyers with the strategic sourcing of biomass. The BioSS framework. The BioSS framework consists of three modes which mirror the development stages of bioenergy projects. BioSS.2 mode for early stage development, BioSS.3 mode for financial close stage and BioSS.Op for the operational phase of the project. BioSS is formed of a fuels library, a supplier evaluation module and an order allocation module, a Monte-Carlo analysis module is also included to evaluate the accuracy of the recommended portfolios. In each mode BioSS can recommend which suppliers should be contracted with and how much material should be purchased from each. The recommended blend should have chemical characteristics within the technological constraints of the conversion technology and also best satisfy the stakeholder group. The fuels library is made up from a wide variety of sources and contains around 100 unique descriptions of potential biomass sources that a developer may encounter. The library takes a wide data collection approach and has the aim of allowing for estimates to be made of biomass characteristics without expensive and time consuming testing. The supplier evaluation part of BioSS uses a QFD-AHP method to give importance weightings to 27 different evaluating criteria. The evaluating criteria have been compiled from interviews with stakeholders and policy and position documents and the weightings have been assigned using a mixture of workshops and expert interview. The weighted importance scores allow potential suppliers to better tailor their business offering and provides a robust framework for decision makers to better understand the requirements of the bioenergy project stakeholder groups. The order allocation part of BioSS uses a chance-constrained programming approach to assign orders of material between potential suppliers based on the chemical characteristics of those suppliers and the preference score of those suppliers. The optimisation program finds the portfolio of orders to allocate to suppliers to give the highest performance portfolio in the eyes of the stakeholder group whilst also complying with technological constraints. The technological constraints can be breached if the decision maker requires by setting the constraint as a chance-constraint. This allows a wider range of biomass sources to be procured and allows a greater overall performance to be realised than considering crisp constraints or using deterministic programming approaches. BioSS is demonstrated against two scenarios faced by UK bioenergy developers. The first is a large scale combustion power project, the second a small scale gasification project. The Bioss is applied in each mode for both scenarios and is shown to adapt the solution to the stakeholder group importance and the different constraints of the different conversion technologies whilst finding a globally optimal portfolio for stakeholder satisfaction.

Out of Challenge, Opportunity: Central America's Electric Sector & Key Issues and Recommendations for Enhanced Regional Electric Integration

Taken together, the six nations of Central America count a population of roughly 40 million people and an energy market equal in size to that of Colombia, sufficient to benefit from economies of scale. The region has traditionally been a net importer of hydrocarbons, and hydroelectricity has dominated electric generation. But more recently, thermoelectric generation (diesel and fuel oil) has greatly increased as a percentage of the regional generation market. Progress has been made across the region’s electric sector, beginning with reforms in the 1990s and the 1996 signing of a regional treaty aimed at the development of a regional energy integration project – the Central American Electrical Interconnection System, or SIEPAC. A fundamental SIEPAC goal is to set up a regional electric market and a regulatory system. Indeed, after many years of development, SIEPAC is poised to open a new chapter in Central America’s electric infrastructure and market. But this new era must contend with critical issues such as the need to consolidate the regional electric market, political issues surrounding the venture, and security concerns. Moreover, local conflicts, in different degrees, have become priorities for policymakers, and these are possible barriers to completing the project. The goals of the SIEPAC project and of deepening the broader electric integration process are possible if national and regional decision makers understand that cooperative decision making will produce better results than separate national decision making. Enhanced regional understanding and cooperative decision making, combined with an effort to reorient the terminology and dialogue vis-à-vis energy efficiency in Central America, form the core recommendations of this paper.