Load forecasting models are of great importance in Electricity Markets and a wide range of techniques have been developed according to the objective being pursued. The increase of smart meters in different sectors (residential, commercial, universities, etc.) allows accessing the electricity consumption nearly in real time and provides those customers with large datasets that contain valuable information. In this context, supervised machine learning methods play an essential role. The purpose of the present study is to evaluate the effectiveness of using ensemble methods based on regression trees in short-term load forecasting. To illustrate this task, four methods (bagging, random forest, conditional forest, and boosting) are applied to historical load data of a campus university in Cartagena (Spain). In addition to temperature, calendar variables as well as different types of special days are considered as predictors to improve the predictions. Finally, a real application to the Spanish Electricity Market is developed: 48-h-ahead predictions are used to evaluate the economical savings that the consumer (the campus university) can obtain through the participation as a direct market consumer instead of purchasing the electricity from a retailer.

Abstract:The objectives of improving the efficiency, and integration, of renewable sources by are complex in practice and should be linked to an increase of demand-side flexibility. The main challenges to achieving this flexibility are the lack of incentives and an adequate framework. For instance, customers' revenue is usually low, the volatility of prices is high and there is not any practical feedback to customers from smart meters. The possibility of increasing customer revenue could reduce the uncertainty with respect to economic concerns, improving investments in efficiency, enabling technology and thus, engaging more customers in these policies. This objective could be achieved by the participation of customers in several markets. Moreover, Demand Response and Energy Efficiency can share ICT technologies but this participation needs to perform an aggregation of demand. The idea of this paper is to present some methodologies for facilitating the definition and evaluation of energy versus cost curves; and subsequently to estimate potential revenues due to Demand Response. This can be accomplished by models that estimate: demand and energy aggregation; economic opportunities and benefits; impacts on customer convenience; customer feedback and price analysis. By doing so, we would have comprehensive information that can help customers and aggregators to define energy packages and their monetary value with the objective of fostering their market participation.

The development of renewable sources in residential segments is basic to achieve a sustainable energy scenario in the horizon 2030–2050 because these segments explain around 25% of the final energy consumption. Demand Response and its effective coordination with renewable are additional concerns for residential segments. This paper deals with two problems: the demonstration of cost-effectiveness of renewables in three different scenarios, and the application of the flexibility of demand, performing as energy storage systems, to efficiently manage the generation of renewable sources while improving benefits and avoiding penalties for the customer. A residential customer in Spain has been used as example. The work combines the use of a commercial simulator to obtain photovoltaic generation, the monitoring of customer to obtain demand patterns, and the development of a Physically-Based Model to evaluate the capability of demand to follow self-generation. As a main result, the integration of models (load/generation), neglected in practice in other approaches in the literature, allows customers to improve revenue up to 20% and reach a basic but important knowledge on how they can modify the demand, development of new skills and, in this way, learn how to deal with the characteristics and limitations of both Demand and Generation when a customer becomes a prosumer. This synergy amongst demand and generation physically-based models boosts the possibilities of customers in electricity markets.

Abstract:In this paper, we propose a novel approach for clustering time series, which combines three well-known aspects: a permutation-based coding of the time series, several distance measurements for discrete distributions and hierarchical clustering using different linkages. The proposed method classifies a set of time series into homogeneous groups, according to the degree of dependency among them. That is, time series with a high level of dependency will lie in the same cluster. Moreover, taking into account the nature of the codifying process, the method allows us to detect linear and nonlinear dependences. To illustrate the procedure, a set of fourteen electricity price series coming from different wholesale electricity markets worldwide was analyzed. We show that the classification results are consistent with the characteristics of the electricity markets in the study and with their degree of integration. Besides, we outline the necessity of removing the seasonal component of the price series before the analysis and the capability of the method to detect changes in the dependence level along time.