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

Valoración de recursos propios en empresas mineras: evidencia y comparación con otros sectores

El capital financiero es muy volátil y si el inversor no obtiene una remuneración adecuada al riesgo que asume puede plantearse el retirar su capital del patrimonio de la empresa y, en consecuencia, producir un cambio estructural en cualquier sector de la economía. El objetivo principal es el estudio de los coeficientes de regresión (coeficiente beta) de los modelos de valoración de activos empleados en Economía Financiera, esto es, el estudio de la variación de la rentabilidad de los activos en función de los cambios que suceden en los mercados. La elección de los modelos utilizados se justifica por la amplia utilización teórica y empírica de los mismos a lo largo de la historia de la Economía Financiera. Se han aplicado el modelo de valoración de activos de mercado (capital asset pricing model, CAPM), el modelo basado en la teoría de precios de arbitraje (arbitrage pricing theory, APT) y el modelo de tres factores de Fama y French (FF). Estos modelos se han aplicado a los rendimientos mensuales de 27 empresas del sector minero que cotizan en la bolsa de Nueva York (New York Stock Exchange, NYSE) o en la de Londres (London Stock Exchange, LSE), con datos del período que comprende desde Enero de 2006 a Diciembre de 2010. Los resultados de series de tiempo y sección cruzada tanto para CAPM, como para APT y FF producen varios errores, lo que sugiere que muchas empresas del sector no han podido obtener el coste de capital. También los resultados muestran que las empresas de mayor riesgo tienden a tener una menor rentabilidad. Estas conclusiones hacen poco probable que se mantenga en el largo plazo el equilibrio actual y puede que sea uno de los principales factores que impulsen un cambio estructural en el sector minero en forma de concentraciones de empresas. ABSTRACT Financial capital is highly volatile and if the investor does not get adequate compensation for the risk faced he may consider withdrawing his capital assets from the company and consequently produce a structural change in any sector of the economy. The main purpose is the study of the regression coefficients (beta) of asset pricing models used in financial economics, that is, the study of variation in profitability of assets in terms of the changes that occur in the markets. The choice of models used is justified by the extensive theoretical and empirical use of them throughout the history of financial economics. Have been used the capital asset pricing model, CAPM, the model XII based on the arbitrage pricing theory (APT) and the three-factor model of Fama and French (FF). These models have been applied to the monthly returns of 27 mining companies listed on the NYSE (New York Stock Exchange) or LSE(London Stock Exchange), using data from the period covered from January 2006 to December 2010. The results of time series and cross sectional regressions for CAPM, APT and FF produce some errors, suggesting that many companies have failed to obtain the cost of capital. Also the results show that higher risk firms tend to have lower profitability. These findings make it unlikely to be mainteined over the long term the current status and could drive structural change in the mining sector in the form of mergers.

Modelling and forecasting fossil fuels, CO2 and electricity prices and their volatilities

In the current uncertain context that affects both the world economy and the energy sector, with the rapid increase in the prices of oil and gas and the very unstable political situation that affects some of the largest raw materials’ producers, there is a need for developing efficient and powerful quantitative tools that allow to model and forecast fossil fuel prices, CO2 emission allowances prices as well as electricity prices. This will improve decision making for all the agents involved in energy issues. Although there are papers focused on modelling fossil fuel prices, CO2 prices and electricity prices, the literature is scarce on attempts to consider all of them together. This paper focuses on both building a multivariate model for the aforementioned prices and comparing its results with those of univariate ones, in terms of prediction accuracy (univariate and multivariate models are compared for a large span of days, all in the first 4 months in 2011) as well as extracting common features in the volatilities of the prices of all these relevant magnitudes. The common features in volatility are extracted by means of a conditionally heteroskedastic dynamic factor model which allows to solve the curse of dimensionality problem that commonly arises when estimating multivariate GARCH models. Additionally, the common volatility factors obtained are useful for improving the forecasting intervals and have a nice economical interpretation. Besides, the results obtained and methodology proposed can be useful as a starting point for risk management or portfolio optimization under uncertainty in the current context of energy markets.

A two-dimensional finite element model of front surface current flow in cells under non-uniform, concentrated illumination

A two-dimensional finite element model of current flow in the front surface of a PV cell is presented. In order to validate this model we perform an experimental test. Later, particular attention is paid to the effects of non-uniform illumination in the finger direction which is typical in a linear concentrator system. Fill factor, open circuit voltage and efficiency are shown to decrease with increasing degree of non-uniform illumination. It is shown that these detrimental effects can be mitigated significantly by reoptimization of the number of front surface metallization fingers to suit the degree of non-uniformity. The behavior of current flow in the front surface of a cell operating at open circuit voltage under non-uniform illumination is discussed in detail.

Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting

In this work, we propose the Seasonal Dynamic Factor Analysis (SeaDFA), an extension of Nonstationary Dynamic Factor Analysis, through which one can deal with dimensionality reduction in vectors of time series in such a way that both common and specific components are extracted. Furthermore, common factors are able to capture not only regular dynamics (stationary or not) but also seasonal ones, by means of the common factors following a multiplicative seasonal VARIMA(p, d, q) × (P, D, Q)s model. Additionally, a bootstrap procedure that does not need a backward representation of the model is proposed to be able to make inference for all the parameters in the model. A bootstrap scheme developed for forecasting includes uncertainty due to parameter estimation, allowing enhanced coverage of forecasting intervals. A challenging application is provided. The new proposed model and a bootstrap scheme are applied to an innovative subject in electricity markets: the computation of long-term point forecasts and prediction intervals of electricity prices. Several appendices with technical details, an illustrative example, and an additional table are available online as Supplementary Materials.