People in shared building space have an important role in energy consumption because they can turn on/off equipment and heat/cooling systems. This behaviour can be influenced by giving then locally tailored context information (energy consumption, temperature, luminosity) and information about the cost of their actions. This paper presents an approach to create personalized local energy consumption predictions in a building using past sensor data, correlated with external conditions to create local context predictions. This prediction is sent in real-time to people’s mobile devices in order to influence their behaviour when increasing or decreasing temperature using heating or cooling systems. This information is essential for sustainability actions in shared spaces, where this information can have an important role. Also, the data (temperature) representation in the building information model (BIM) module can help the user understand environment conditions and, together with the user sharing their thermal feelings, can be used to change behaviour. This approach using BIM’s representation models allows Things2People interaction to improve energy savings in these shared spaces.

--

BIM,Change behaviour,People interaction,Power management,Predictions,Internet of Things

• Computer and Information Sciences - Natural Sciences
• Electrical Engineering, Electronic Engineering, Information Engineering - Engineering and Technology