Numerous tools and approaches are evolving towards the support of data mining and analysis processes, focusing on part or the overall lifecycle of such processes. In parallel, penetration of data analytics tools in the market is continuously increasing, along with their adoption by various stakeholders, including data scientists, decision and policy makers and business analysts. However, given the wide diversity in the needs for realizing an analysis and the level of expertise of the various stakeholders, there is a need for design and implementation of analysis toolkits that can support part or the overall lifecycle of an analysis process, without imposing dependencies on the type of tool or technology to be used. In the current manuscript, an approach for detaching the design, development and execution of big data analysis processes is detailed, focusing on the realization of energy and behavioral analytics, targeted to supporting the increase of energy efficiency in smart buildings through behavioral change of the citizens. The overall architectural approach as well as the set of energy and behavioral analysis processes integrated are detailed.
[1]
Stamatis Karnouskos,et al.
Impact assessment of smart meter grouping on the accuracy of forecasting algorithms
,
2013,
SAC '13.
[2]
Antonio F. Gómez-Skarmeta,et al.
Providing Personalized Energy Management and Awareness Services for Energy Efficiency in Smart Buildings
,
2017,
Sensors.
[3]
Ian Walker,et al.
How smart do smart meters need to be?
,
2017
.
[4]
Marimuthu Palaniswami,et al.
Improving load forecasting based on deep learning and K-shape clustering
,
2017,
2017 International Joint Conference on Neural Networks (IJCNN).
[5]
Antonio F. Gómez-Skarmeta,et al.
Data driven modeling for energy consumption prediction in smart buildings
,
2017,
2017 IEEE International Conference on Big Data (Big Data).