Automated decision tools, such as advanced energy management systems, are required to involve the electrical grid users in energy flexibility services. This paper focuses on the prediction models as a substantial part of decision strategy in advanced energy management systems and on advanced energy management systems as a tool that supports the active involvement of electrical grid users in energy flexibility services. Prediction models' desired properties are self-establishing and self-adaptation, which require new solutions in data selection, filtering, processing and model learning. Some of these properties are investigated within this paper.