COLLECTIONS

Documents published in Scipedia

• Comparing time-series clustering approaches for individual electrical load patterns

  Z. Greve, F. Lecron, F. Vallée, G. Mor Martinez, D. Pérez

  CIRED-Open Acces Proceedings Journal (2017). Vol. 2017 (1), pp. 2165-2168

  
  

  Abstract

  This work positions the task of grouping electricity load time series among the vast field of clustering, and highlights corresponding research issues. A selection of the most performant time-series clustering approaches from the signal processing community are compared on the same dataset, composed by domestic electricity load profiles from Spain. The cross-correlation-based distance of Paparrizos and Gravano (2015) is shown to provide the best trade-off between clustering accuracy and CPU times

  Abstract
  This work positions the task of grouping electricity load time series among the vast field of clustering, and highlights corresponding research issues. A selection of the [...]

  • 1
  •  read

• Using matrix factorisation for the prediction of electrical quantities

  F. Lecron, Z. Grève, F. Vallée, G. Mor Martinez, D. Pérez, S. Danov, J. Cipriano

  CIRED-Open Acces Proceedings Journal (2017). Vol. 2017 (1), pp. 2568-2571

  
  

  Abstract

  The prediction task is attracting more and more attention among the power system community. Accurate predictions of electrical quantities up to a few hours ahead (e.g. renewable production, electrical load etc.) are for instance crucial for distribution system operators to operate their network in the presence of a high share of renewables, or for energy producers to maximise their profits by optimising their portfolio management. In the literature, statistical approaches are usually proposed to predict electrical quantities. In the present study, the authors present a novel method based on matrix factorisation. The authors' approach is inspired by the literature on data mining and knowledge discovery and the methodologies involved in recommender systems. The idea is to transpose the problem of predicting ratings in a recommender system to a problem of forecasting electrical quantities in a power system. Preliminary results on a real wind speed dataset tend to show that the matrix factorisation model provides similar results than auto regressive integrated models in terms of accuracy (MAE and RMSE). The authors' approach is nevertheless highly scalable and can deal with noisy data (e.g. missing data).

  Abstract
  The prediction task is attracting more and more attention among the power system community. Accurate predictions of electrical quantities up to a few hours ahead (e.g. renewable [...]

  • 1
  •  read

• Developing indicators to improve energy action plans in municipalities: An accounting framework based on the fund-flow model

  X. Cipriano, G. Gamboa, S. Danov, G. Mor Martinez, J. Cipriano

  Sustainable Cities and Society (2017). Vol. 32, pp. 236-276

  
  

  Abstract

  The main instrument used to implement the EU 2020 objectives at local level is the Covenant of Mayors, which fosters the development of Sustainable Energy Action Plans (SEAPs); these plans aim to reduce CO2 emissions by at least 20% by 2020. These action plans are linked to different municipal promotion tools, and a set of indicators has also been proposed to define and monitor the actions. In general, the adequacy of the main indicators used by the SEAPs is analysed, taking into consideration the representation of the urban system across all scales (city, neighbourhood and building) as well as whether the chosen indicators enable the analyst to consider the influence of human activities (i.e. hours of use) on energy consumption, within the system. In contrast, this paper proposes to apply the fund-flow model as an accounting framework that can be used to develop indicators for energy-efficient urban planning. The energy model behind these indicators was obtained using an innovative procedure for energy simulation which considers the isolated characteristics of the buildings (type of construction, occupation, interior comfort, type of energy system) as well as the interaction with the surrounding buildings (shadows, streets, geometry).The indicators proposed have been developed within the SEMANCO UE project, and we have taken into account their potential as criteria for identifying the most effective actions for energy planning on multilevel scales. An example in Manresa (Spain) is used to test the usability. Our results demonstrate that these indicators are suitable for use in decision-making processes in the field of urban planning and for performing coherent comparisons of actions between urban areas, cities, countries or regions.

  Abstract
  The main instrument used to implement the EU 2020 objectives at local level is the Covenant of Mayors, which fosters the development of Sustainable Energy Action Plans (SEAPs); [...]

  • 1
  •  read

• EMPOWERING, a smart Big Data framework for sustainable electricity suppliers

  G. Mor Martinez, J. Vilaplana, S. Danov, J. Cipriano, F. Solsona, D. Chemisana

  IEEE Access (2018). Vol. 6, pp. 71132-71142

  
  

  Abstract

  This paper presents the EMPOWERING project, a Big Data environment aimed at helping domestic customers to save electricity by managing their consumption positively. This is achieved by improving the information received about energy bills and offering online tools. The main contributions of EMPOWERING are the creation of a novel workflow in the electricity utility sector regarding the implementation of data analytics for their customers and the fast implementation of data-mining techniques in massive datasets within a Big Data platform to achieve scalability. The results obtained show that EMPOWERING can be of use for customers of electrical suppliers by changing their energy habits to decrease consumption and so increase environmental sustainability.

  Abstract
  This paper presents the EMPOWERING project, a Big Data environment aimed at helping domestic customers to save electricity by managing their consumption positively. This is [...]

  • 3
  •  read