An innovative approach to design cogeneration systems based on big data analysis and use of clustering methods

In recent years, collecting energy consumption data is becoming easier and easier thanks to decreasing of cost of smart sensors. Moreover, capacity of analysis data using big data methods like machine learning and artificial intelligence is increasing. Such methods are expected to be useful to increase efficiency of energy systems. In this paper an innovative approach to design cogeneration systems based on big data analysis is developed. More specifically, a study on how cluster analysis could be applied to analyse energy consumption data is depicted. The aim of the method is to design cogeneration systems that suit more efficiently energy demand profiles, choosing the correct type of cogeneration technology, operation strategy and, if they are necessary, energy storages. In the first part of the paper, the methodology based on clustering to perform the analysis of the dataset is described. In the second part, a case study with cogenerators (a wood industry that requires low temperature heat to dry wood into steam-powered kilns) is analysed. An alternative cogeneration system is designed and proposed. Thermodynamics benchmarks are defined to evaluate differences between as-is and alternative scenarios. Results show that the proposed innovative method allows to choose a more suitable cogeneration technology compared to the adopted one, giving suggestions on the operation strategy in order to decrease energy losses and, consequently, primary energy consumption.