The backbone of the RE–COGNITION Platform is the Automated Cognitive Energy Management Engine (ACEME).
The main objective of ACEME is to provide optimal energy dispatch among the various RES while considering the respective energy prices. It is realized through real-time information and interaction between the field devices of the different building networks.
The ambitious goal of the ACEME is to ensure the highest possible level of RES penetration by taking automated control decisions based on the aforementioned complex inputs.
ACEME will be able to receive measurements from the building energy-consuming devices and predict patterns for the aggregated load per building, having the ability to extract data from local building management systems (BMS) or work with arbitrary/generic information through intelligent energy disaggregation.
Through its simple interfacing with on-site environmental sensors and the ability to acquire weather information from local station units (on-line weather services), it will be able to predict RES generation within various time intervals.
The Automated Cognitive Energy Management Engine (ACEME) of RE-COGNITION aims to exploit a multi-agent framework in order to perform the algorithmic control strategies posed by its intelligent entities, providing an end-to-end Intelligent Management system solution, applicable to a variety of renewable energy technologies and building management systems.
Status of activities
Towards this end, the initial agent-based framework of ACEME has already been developed.
Furthermore, the connection among the Agents has been established successfully. The validation of the multi-agent framework has been carried out through its integration and testing at the RE-COGNITION pre-pilot site; CERTH/ ITI SmartHome. This effective operation of ACEME was demonstrated during the project’s 1st review meeting, as well.
As RE-COGNITION project evolves, the ACEME optimization tool continuously expands to interface with all the project’s assets, addressing the specific pilot’s needs, aiming towards a state, where it constitutes a holistic energy management solution.
Simulation results of Smart Home implementation, a) Custom scenario b) Optimization with ACEME