Reglas de asociación difusas en Big Data

• Autores: Carlos Jesús Fernández Basso
• Directores de la Tesis: María Dolores Ruiz Jiménez (dir. tes.) , María José Martín Bautista (dir. tes.)
• Lectura: En la Universidad de Granada ( España ) en 2020
• Idioma: español
• Número de páginas: 272
• Enlaces
  • Tesis en acceso abierto en: DIGIBUG
• Resumen

  • This paper has reviewed the field of Data Science and how Data Science techniques can be applied to building energy management. Specifically, we have focused on building operation, energy load prediction, and identification of consumption patterns. Our experiments show that Big Data technologies can solve the computational problems that appear when processing of large amounts of data, which are likely to have an increasing relevance with the advent of the Internet of Things –with smart meters and appliances fully connected to the Internet. However, the applications to real-world scenarios are still scarce. In our experience, one of the most important aspects to improve is achieving a greater involvement of the building managers in the data analysis process. To do this, future research work should explore two complementary directions, namely, showing the potential of Data Science to building managers, and developing more user-friendly algorithms and tools. In this way, we expect that new approaches will be less opaque, easier to use, more customizable, and above all other features, more engaging.