Forecasting Indoor Temperature Based on a Time Series Dataset


Description | Ambiosfera is a consulting company providing energy certification, environmental sustainability and environmental management services. The company developed a project, named Ambiosensing, to balance environmental indoor comfort and energy consumption. For that, it was created a sensor that does the energetic monitoring of buildings by collecting, daily and minute by minute, environmental indoor data, such as temperature.

Ambiosfera aims to develop predictive models to anticipate indoor environmental scenarios and, in this way, manage energy consumption more efficiently. These models may help to ensure better energy performance and, consequently, better energy management.

Can we predict indoor environment evolution based on past patterns?

The purpose of this challenge is to develop a forecasting model for indoor temperature based on a time series dataset collected from January 23th, 2021, to March 5th, 2022.


Mathematical background | Time Series Analysis, Time Series Forecasting.


Industrial partner | Miguel Duarte, Ambiosfera, Monte da Caparica, Portugal


Coordinators | Joana Vieira and Regina Bispo, NOVA University of Lisbon



 

Send email





Support
8IMW is supported by the Department of Mathematics of the University of Coimbra and by the Center of Mathematics of the University of Coimbra through project FCT UIDB/MAT/00324/2020.












Collaboration