Smart Flows

Purpose and goal

Smart Flow aimed at applying AI within process industry through using machine learning, industrial IoT and cloud technology, specifically in the case of district heating. The goal was to make a concept evaluation of AI for decision support in a core industrial process. The project has through a successful concept evaluation shown the technological possibilities and the economic potential within the energy utility application. Furthermore, the project has identified many challenges related to industrial use of AI.

Expected results and effects

- Successful development of AI algorithms for prediction of heat demand and network propagation delays and temperature losses. - A pilot architecture in the cloud managing many thousands of building meters in real-time. - Multiple articles in sector specific media, e.g. Fjärrvärmetidningen and Nordiska projekt. - Widespread dissemination of result through industrial events such as Internetdagarna, Microsoft´s och Dagens Industri´s AI event. - A movie describing the project have been produced by Microsoft and is presented at their global site for industrial customer stories.

Planned approach and implementation

A great success factor has been the way of working and the cooperation within the project. The project goals were well aligned with Mälarenergi vision. In addition, Mälarenergi have been very active in the project work, with frequent recurring work meetings. Another key factor has been the creation of a multi-role group, within the Mälarenergi organisation, that worked with data identification, quality, documentation, and correction. In total Mälarenergi estimate that more than 50 people within the organization have been involved in the project at varying degree.

External links

https://www.sics.se/projects/smarta-floden