PV self-consumption prediction methods using supervised machine learning

KTH Royal Institute of Technology, Stockholm, Sweden

^* corresponding author: nelson.sommerfeldt@energy.kth.se

Abstract

The increased prevalence of photovoltaic (PV) self-consumption policies across Europe and the world place an increased importance on accurate predictions for life-cycle costing during the planning phase. This study presents several machine learning and regression models for predicting self-consumption, trained on a variety of datasets from Sweden. The results show that advanced ML models have an improved performance over simpler regressions, where the highest performing model, Random Forest, has a mean average error of 1.5 percentage points and an R² of 0.977. Training models using widely available typical meteorological year (TMY) climate data is also shown to introduce small, acceptable errors when tested against spatially and temporally matched climate and load data. The ability to train the ML models with TMY climate data makes their adoption easier and builds on previous work by demonstrating the robustness of the methodology as a self-consumption prediction tool. The low error and high R² are a notable improvement over previous estimation models and the minimal input data requirements make them easy to adopt and apply in a wide array of applications.