Towards a multilevel energy saving model for smart cities

As a result of rural and suburban migration to the cities, urban life has become a significant challenge for citizens and mayors, imposing a huge concern in the sustainable use of resources like energy, water, transportation and housing. Smart cities are the biggest bet to address these challenges efficiently through a real-time monitoring approach which aims to assist in intelligent planning and sustainable urban development. However, to accomplish this monitoring efficiently and to enable the sustainable use of resources, it is necessary an integration between citizens, city devices and the platform where the data is stored and processed. In this context, we are proposing the 3LES model (3 Levels of Energy Saving for Smart Cities), a model that combines data from citizens, city devices and nodes from the processing plataform to offer a multilevel energy saving proposal. 3LES must act transparently without affecting the quality of the services already offered in the city. This paper presents the components of management and monitoring of power consumption at various levels, as well as a model that monitors the energy consumption of elastic cloud applications. The results are promising, with a model that allows the estimation of the energy consumption of elastic applications based on CPU and memory traces with an average and median precision of 97.15% and 97.72%. In addition, we obtained a reduction of more than 90% in the energy spent in public lighting in the city of Rome when analyzing the citizens' location.