Unsupervised grouping of industrial electricity demand profiles: Synthetic profiles for demand-side management applications

Demand side management is a promising alternative to offer flexibility power systems with high shares of variable renewable energy sources. Numerous industries possess large demand potentials but accounting for them in system analysis and modelling restricted by the availability their data, which are usually confidential. In this study, methodology synthetize anonymized hourly electricity consumption profiles calculate potential proposed. This combines different partitioning hierarchical clustering techniques regression analysis. The applied three case studies Chile: two pulp paper industry plants one food plant. A significant hourly, daily annual found cases (15%–75%). Moreover, resulting share same statistical characteristics as measured can be used exercises without confidentiality issues.