Detalhes bibliográficos
| Ano de defesa: |
2020 |
| Autor(a) principal: |
Alves, Ânderson Pinto
 |
| Orientador(a): |
Manssour, Isabel Harb
|
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Pontifícia Universidade Católica do Rio Grande do Sul
|
| Programa de Pós-Graduação: |
Programa de Pós-Graduação em Ciência da Computação
|
| Departamento: |
Escola Politécnica
|
| País: |
Brasil
|
| Palavras-chave em Português: |
|
| Palavras-chave em Inglês: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
http://tede2.pucrs.br/tede2/handle/tede/9239
|
Resumo: |
Due to the recent technological evolution, new sensors and devices are being incorporated in buildings and smart cities, to facilitate the understanding of its dynamics and improve its management, as well as its cost-benefit ratio. In this context, the combination of information technology and devices capable of capturing and sharing information with other devices can help to collect and understand energy data. This is an important task to assess energy efficiency, helping to solve energy-related problems. However, it can become a challenge to analyze large volumes of data that are collected and stored continuously to confirm trends, identify hidden patterns and outliers that help in decision making. The use of graphical representations can assist in this process, but the visual analysis of large volumes of energy data may not be a simple task to be performed, as many of the existing visualization tools were not designed for this purpose, making it so difficult for an interactive analysis with different levels of granularity over time, such as comparing meteorological data with different energy data. Thus, the objective of this work is to present a model for visual analysis of consumption data or energy generation for cities and smart buildings. This model allows to load, analyze and compare energy data and meteorological data over time to, for example, identify consumption patterns with different climatic conditions and outliers. In addition, it offers several ways to explore and understand patterns between different sets of data, incorporates four algorithms to perform predictive analysis and allows to evaluate data with different levels of time granularities, through an interactive approach based on the integrated on-demand detail technique com coordinated multiple views. An evaluation with domain experts demonstrates the feasibility, in addition to the advantages of using this model to explore, monitor and compare energy data. |
