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

In recent years, collecting energy consumption data has become easier thanks to the decreasing of smart sensors cost. Moreover, the capacity of data analysis using big data methods like machine learning and artificial intelligence has increased. Such methods are expected to be useful to increase the efficiency of energy systems. In this paper, an innovative approach based on big data analysis to design cogeneration systems is presented. More specifically, this study describes how cluster analysis can be applied to analyse energy consumption data. The aim of the method is to design cogeneration systems that can suit energy demand profiles more efficiently, choosing the correct type of cogeneration technology, operation strategy and, if they are necessary, the size of energy storages. In the first part of the paper, the method based on clustering to perform the analysis of the dataset is described. In the second part, a case study based on a cogeneration plant (a wood industry that requires low temperature heat to dry wood into steam-powered kilns) is analysed. An alternative cogeneration system is designed by means of the proposed method in terms of the choice of the cogeneration technology, the sizing of thermal storage, and the operation strategy of the plant. Thermodynamic and economic benchmarks are defined to evaluate the differences between as-is and alternative scenarios. Results show that the proposed innovative method is useful to design cogeneration systems for industry allowing energy and economic savings.