Smart Markets for Real-Time Allocation of Multi-Product Resources: The Case of Shared Electric Vehicles

Abstract

Motivated by the deep transformation of the transportation sector toward electric and shared mobility, this research develops a decision support tool that enables real-time allocation of shared electric vehicles (SEVs) to either the rental market, or - aggregated as a virtual power plant (VPP) - to the electricity market. This multi-purposing of SEVs beyond the traditional scope of mobility services can boost utilization and profitability for fleet operators while also facilitating the integration of variable rate renewable energy sources. We abstract this setting to the general problem of real-time multi-product resource allocation via smart markets. Due to a lack of suitable techniques in the literature, we develop our own general approach that leverages highly digitized real-time markets and intelligent agents to enable dynamic multi-product resource allocation. Agents continuously evaluate which markets are most attractive and strategically and iteratively place bids in the respective markets on the resource owner's behalf until all resources have been committed for a specific period. We contribute a general framework that provides a blueprint for similar multi-product resource allocation settings and demonstrate its efficacy in the domain of SEV fleets by developing tailored analytics and machine learning based solution approaches along the dimensions of this framework.

Keywords: Smart Markets, Intelligent Agents, Electric Vehicles, Virtual Power Plants