Aristotle University Of Thessaloniki (AUTH)
Artificial intelligence methods for the management of electric vehicles in the smart grid
Abstract
dc:descriptionThe electrification of transport, via the extensive use of Electric Vehicles (EVs) is seen as one of the main pathways to achieve significant reductions in CO2 emissions. To control the activities of EVs will demand algorithms that can solve problems that involve many heterogeneous entities, each one having its own goals, needs and incentives, while they will operate in highly dynamic environments and having to deal with several uncertainties. Artificial intelligence techniques have been proven efficient in solving such problems. In the first part of this thesis, we provide a survey of the literature to identify the main research problems and describe the commonalities and key differences in the approaches. Later, we study the problem of allocating EVs to charging stations and scheduling their charging. In doing so, we develop three different approaches: 1) We develop offline and online solutions that treat EV users as self-interested agents that aim to maximize their profit and minimize the impact on their schedule. We formulate the problem of the optimal EV to charging station allocation as a Mixed Integer Programming (MIP) one and we propose two pricing mechanisms. 2) We apply dynamic pricing techniques to balance EV demand across a set of charging stations. 3) We apply agent-based negotiation techniques between the stations and EVs in order to service EVs when the MIP problem is initially unsolvable. Later, we study a setting where EVs can be hired to drive from pick-up to drop-off points in a Mobility-on-Demand (MoD) scheme. The goal of the system is, either to maximize the number of serviced customers, or the total EV utilization. We initially characterize the optimization problem as a max-flow problem. We then model and solve the EV-to-trip scheduling problem offline and optimally using MIP techniques and show that the solution scales up to medium sized problems. Given this, we develop two non-optimal algorithms, namely an incremental-MIP and a greedy heuristic algorithm for larger problems. Moreover, we develop a tabu search-based local search technique to further improve the solution of the non-optimal algorithms. In addition, we study the problem of the efficient charging and dis-charging of EVs at a charging station level. Initially, we formulate the problem as a MIP one and we solve it optimally assuming full knowledge of EV demand and energy generation. Later, we propose an online algorithm that iteratively calls the offline one and copes with unknown future interruptions by arriving EVs and with the inability to predict accurately renewable energy production. Finally, we present a tool and a Java library for the efficient simulation of the charging of large numbers of EVs. In this vein, EVLibSim is a tool for the simulation of EV activities at a charging station level. EVLibSim unifies EVLib's primary functions such as the charging and dis-charging of batteries, battery swapping, as well as parking/inductive charging. EVLib is a Java library that provides a simple, yet efficient framework for the management of several EV activities, at a charging station level, within a smart grid.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2018
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Rigas, Emmanouil
- Ρήγας, Εμμανουήλ
Subjects
dc:subject × 20- Ηλεκτρικό όχημα
- Τεχνητή νοημοσύνη
- Βελτιστοποίηση
- Αλγόριθμοι αναζήτησης
- Αλγόριθμοι τοπικής αναζήτησης
- Συστήματα πολλαπλών πρακτόρων
- Σχεδιασμός Μηχανισμών
- Ευφυή δίκτυα ηλεκτροδότησης
- Electric vehicle
- Artificial intelligence
- Optimization
- Search algorithms
- Local search
- Multi agent systems
- Mechanism design
- Smart grid
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Natural Sciences
- Computer and Information Sciences
Rights
dc:rights- Statement dc:rights
-
- BY_NC_ND
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/44843