Swiss scientists develop machine learning algorithm to optimize home solar-plus-storage

A group of researchers from Switzerland's ETH Zurich – Swiss Federal Institute of Technology and Germany's University of Bamberg has developed a techno-economic simulation model based on a machine learning algorithm, which is aimed at optimizing configuration and profitability of residential solar-plus-storage power systems. In the paper, Economic assessment of photovoltaic battery systems based on household load profiles, the research team has created its model on the basis of real-world energy consumption data from 4,190 Swiss households, which were taken under current electricity rates and weather conditions in Zurich. The authors of the study stressed, however, that their algorithm is based only on a limited set of features, and on shorter measurement time-frames of smart-meter data. Several cost scenarios were presented in the research, the most optimistic of which envisages that the installation of a residential photovoltaic-battery (PVB) system, with a mean installed PV power of 4.4 kW and a mean battery size of 9.6 kWh, will be profitable for 99.9% of Swiss households. Under this scenario, the cost of residential solar is expected to be under €1,000 per kW of PV installed, while that of the battery will not exceed €250 per kWh.