Smart Meter Data and Operating Envelopes in LV Networks: A Model-Free Approach

The adoption of distributed energy resources creates opportunities for end users to provide system-level services through aggregators. Nonetheless, simultaneous power exports/imports from end users can cause challenges in low voltage (LV) networks. While operating envelopes (OEs), i.e., time-varying export/import limits, can help, their correct calculation would require power flows, which can be challenging as accurate LV network models are rarely available. Using historical smart meter data and neural networks, this paper proposes a scalable electrical model-free approach to calculate OEs. Model-free voltage calculations, asset utilization approximations, and a heuristic algorithm are used to assess different export/import values of end users and, thus, determine their OEs. The approach is demonstrated using real smart meter data from an Australian LV network (155 customers). Results not only demonstrate the accuracy of voltage calculations but also consistency of model-free OE values, suggesting is an alternative to calculate OEs in the absence of electrical models.