Effect of Demand Forecast Error on Imbalance Cost in Residential Micro Grid

Abstract

In this paper, we conduct electric power simulation by forecasting electricity demand in general households with PV power generation based on the current electricity supply and demand system in Japan. Specifically, forecast errors for electricity demand in general households are taken into account, and machine learning is used to forecast the output of residential photovoltaic power generation. The actual electricity demand, which is the difference between the electricity demand in general households and the PV output, is then calculated, and the degree of contribution of the assumed model to the electricity system is evaluated using an index called imbalance cost from the perspective of a retail electricity provider.