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

摘要

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