Advanced Multi-objective optimization of Energy management systems using Deep neural networks and HPC for real-time, multi-step
energy forecasting

Duration: 29. 1. 2025 - 29. 4. 2026

Project title: Advanced Multi-objective optimization of Energy management systems using Deep neural networks and HPC for real-time, multi-step energy forecasting

Project acronym: AIMED-HPC

Project Coordinator: Robotina d.o.o.

Project Partners: Rudolfovo, University of Ljubljana

Project type: Business experiment, Fortissimo Plus, HE

Total project value: 192.000 EUR

Project value for Rudolfovo: EUR 75,999

Project leader at Rudolfovo: Dr Jelena Joksimović (jelena.joksimovic@rudolfovo.eu)

Brief description of the project:

Robotina aims to revolutionise energy management in buildings (offices, hotels, shopping malls, public institutions) with a subscription service that combines real-time data and artificial intelligence (AI) to optimise energy consumption, reduce costs and improve sustainability for end-users. The service works with any building management system (BMS) and is based on a local EMS with an EDGE computer that optimises consumption according to weather conditions, energy prices and tariffs.

Robotina uses hybrid machine learning models, mainly BiLSTM and MLP, to efficiently predict energy consumption (1-3 days in advance, with 15-minute accuracy). However, providing these forecasts to more than 10,000 users is computationally challenging, given that current CPU solutions require about one week to train a BiLSTM model with weekly data.

Therefore, the use of High Performance Computing (HPC) is crucial for efficient data processing and large scale model implementation. The use of HPC will allow Robotina to expand its market opportunities and consolidate its leadership in energy management.

The Advanced Multi-objective Optimisation of Energy Management - AIMED-HPC business experiment has received funding through the FFplus project, which is funded by the European Association for High Performance Computing (HPC) under grant agreement No 101163317. HPC receives support from the Horizon Europe programme of the European Union.