As a prerequisite for the optimization of the operation plans, Smarticity generates machine learning models of the internal energy production and loads, based on data acquired during the energy system exploitation. These models can be further improved by using publicly available data on weather, working and non-working days, specifics related to RES incentives, etc.
To create and maintain these models, Smarticity employs Blackfox, Vodéna’s Cloud service for automated generation of optimized machine learning models, based on Deep Neural Networks, Random Forest and XGBoost. Black Fox performs genetic algorithm (GA) optimization of all elements of the machine learning model with the aim of generating a model that best describes input data.
These models enable simulation of the data chain for any hypothetic operation plan. The results obtained from the simulations, along with all other grid features and external factors, are subjected to an optimization process in order to find the energy management pattern that results with the most economical usage of electricity under given conditions. This solution offers to end users in the form of SaaS, thus enabling them to optimize energy usage without investment in scarcely available data science and optimization experts, or in the necessary computing infrastructure.