Solar power forecasting in smart grids using distributed information

Abstract

The growing penetration of solar power technology at low voltage (LV) level introduces new challenges in the distribution grid operation. Across the world, Distribution System Operators (DSO) are implementing the Smart Grid concept and one key function, in this new paradigm, is solar power forecasting. This paper presents a new forecasting framework, based on vector autoregression theory, that combines spatial-temporal data collected by smart meters and distribution transformer controllers to produce six-hour-ahead forecasts at the residential solar photovoltaic (PV) and secondary substation (i.e., MV/LV substation) levels. This framework has been tested for 44 micro-generation units and 10 secondary substations from the Smart Grid pilot in Évora, Portugal (one demonstration site of the EU Project SuSTAINABLE). A comparison was made with the well-known Autoregressive forecasting Model (AR-univariate model) leading to an improvement between 8% and 12% for the first 3 lead-times.