Energy Management for Solar-Powered Electric-Bus Charging Station: A Data-Driven Method

TL;DR

This paper develops a data-driven energy management system for solar-powered electric bus charging stations, effectively handling uncertainties in solar output, prices, and bus schedules through advanced surrogate modeling.

Contribution

It introduces a novel data-driven polynomial chaos expansion surrogate and nonparametric inference to optimize energy management under uncertainty.

Findings

The proposed EMS improves energy efficiency and cost savings.

The data-driven method effectively manages uncertainties with limited data.

Case studies validate the approach's effectiveness.

Abstract

This paper presents a flexible energy management system (EMS) for an electric bus charging station (EBCS) that integrates renewable generation, energy storage, and electric bus (EB) charging while accounting for uncertainties in solar PV output, electricity prices, and EB arrival/departure state of charge. A data-driven polynomial chaos expansion surrogate is developed from a limited set of uncertainty samples, and a nonparametric inference method is used to enrich the input data when historical data is limited. Case studies on a solar-powered EBCS with 20 EBs demonstrate the effectiveness of the proposed EMS and data-driven method.