Abstract:

The need for more flexible power usage is increasing due to the electrification of new societal sectors and more significant amounts of integrated intermittent electricity production in the power system. Among other cities, Uppsala in Sweden is undergoing an accelerated transition of its vehicle fleet from fossil combustion engines to electric vehicles. To meet the requirements of the transforming mobility infrastructure, Uppsala municipality has, in collaboration with Uppsala University, built a full-scale commercial electrical vehicle parking garage equipped with a battery storage and photovoltaic system. This paper presents the current hardware topology of the parking garage, a neural network for day-ahead predictions of the parking garage’s load profile, and a simulation model in MATLAB using rule-based peak shaving control. The created neural network was trained on data from 2021, and its performance was evaluated using data from 2022. The rule-based peak shaving control performance was evaluated using the predicted load demand and photovoltaic data collected for the parking garage. This paper aims to test a prediction model and peak shaving strategy that could be implemented in practice on-site at the parking garage. The created neural network has a linear regression index of 0.61, which yielded a satisfying result when used in the rule-based peak-shaving control with the parking garage’s 60 kW/137 kWh battery system. The peak shaving model reduced the highest load demand peak of 117 kW by 38.6% using the forecast of a neural network.