Forecasting of Electric Energy Consumption for Housing Cooperative with a Grid Connected PV System

Abstract

Our research aims to develop an adaptive control system for photovoltaic systems with energy storage that adapts after changing different kinds of conditions. In particular, for efficient controlling of battery storage, the precise prediction of electricity consumption is required. Due to the complexity of the proposed research, in this paper, we proposed the simplification of the complexity of the long short-term memory model for the forecasting of the electric energy consumption from a house cooperative in Karlstad, Sweden. Based on the experimental results, there is a 1.233 kWh of mean absolute error and 1.859 kWh of root-mean square error for the predicted energy consumption (validated from testing data collected 7 days after the collected training data for the selected deep learning model).