On the Effectiveness of Temporal Data Aggregation in Indoor IoT Systems

Temporal Data Aggregation is a mechanism that aims to minimize bandwidth and energy consumption in wireless sensor networks (WSN). To the best of our knowledge, most of the works in literature investigated such mechanism in outdoor uses-cases, where the physical quantities are often stationary. Little attention have been given to indoor environments, such as schools, houses or offices. The challenge lies in the unpredictable nature of variables in these environments due to human activities, which cause abrupt changes in data values. This paper investigates the effectiveness of temporal data aggregation in indoor environments. The study relays on data sets that were collected in three real-world environments: a smart home, a research laboratory with multiple offices and a primary school. Results analysis demonstrate that temporal aggregation using time series forecasting models can significantly reduce data transmission rates and energy consumption while preserving the accuracy of collected data. Those findings demonstrate the potential of temporal data aggregation in extending the longevity of IoT (Internet of Things) infrastructures, even in indoor environments impacted by human activities.