Optimal Autonomous Charging of Electric Vehicles with Stochastic Driver Behavior

Donadee, Jonathan; Ilić, Marija; Karabaşoğlu, Orkun

doi:10.1109/vppc.2014.7007115

Cited by 15 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mingfei and Jilai [9] studied the regular behavior process of the private electric vehicle clusters to model the EVs charging demand. Donadee et al [10] developed a method for optimal autonomous charging of EVs for the estimated energy demand that is based on collected driving patterns. Power system operation requires accurate estimation of the increased energy demand due to EV charging.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimal Operation of Interdependent Power Systems and Electrified Transportation Networks

Amini

Karabaşoğlu

2018

Energies

Self Cite

View full text Add to dashboard Cite

Electrified transportation and power systems are mutually coupled networks. In this paper, a novel framework is developed for interdependent power and transportation networks. Our approach constitutes solving an iterative least cost vehicle routing process, which utilizes the communication of electrified vehicles (EVs) with competing charging stations to exchange data, such as electricity price, energy demand, and time of arrival. EV routing problem is solved to minimize the total cost of travel using the Dijkstra algorithm with the input from EVs battery management system, electricity price from charging stations, powertrain component efficiencies, and transportation network traffic conditions. Through the bidirectional communication of EVs with competing charging stations, EVs charging demand estimation is done much more accurately. Then, the optimal power flow problem is solved for the power system, to find the locational marginal price at load buses where charging stations are connected. Finally, the electricity prices are communicated from the charging stations to the EVs, and the loop is closed. Locational electricity price acts as the shared parameter between the two optimization problems, i.e. optimal power flow and optimal routing problem. Electricity price depends on the power demand, which is affected by the charging of EVs. On the other hand, location of EV charging stations and their different pricing strategies might affect the routing decisions of the EVs. Our novel approach that combines the electrified transportation with power system operation, holds tremendous potential for solving electrified transportation issues and reducing energy costs. The effectiveness of the proposed approach is demonstrated using Shanghai transportation network and IEEE 9-bus test system. The results verify the cost-savings for both power system and transportation networks.The idea, framework, methodology, and required hardware for the proposed method in this article is patent pending [P1].[P1] Mohammadhadi Amini and Orkun Karabasoglu, US Patent Office Application #62/494,289, "Optimization of the interdependent electrical power and electrified transportation networks considering intelligent routing of electric vehicles and charging stations pricing strategy: framework and methodology",

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Optimal Operation of Interdependent Power Systems and Electrified Transportation Networks

Amini

Karabaşoğlu

2018

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Methods using artificial intelligence such as reinforcement learning (RL) or artificial neural network to solve the challenges of single PEV charging scheduling are gaining popularity in research. Methods using existing user behaviour data to schedule a single PEV are examined in [30][31][32]. The authors of [30] use an artificial neural network trained using historical household power comsumption and EV energy demand data with two hidden layers to predict whether the PEV should charge or discharge.…”

Section: Literature Reviewmentioning

confidence: 99%

“…This proposal achieved good results under the assumption that the user behaviour is known ahead of time. Two infinite horizon average cost MDP formulations are described for both hybrid vehicles and PEVs in [32]. The MDPs are built from historical data on vehicle usage.…”

Section: Literature Reviewmentioning

confidence: 99%

Autonomous PEV Charging Scheduling Using Deep-Q Network and Dyna-Q Reinforcement Learning

Wang¹

2021

Preprint

View full text Add to dashboard Cite

This paper proposes a demand response method that aims to reduce the long-term charging cost of a plug-in electric vehicle (PEV) while overcoming obstacles such as the stochastic nature of the user’s driving be- haviour, traffic condition, energy usage, and energy price. The problem is formulated as a Markov Decision Process (MDP) with unknown transition probabilities and solved using deep reinforcement learning (RL) techniques. Existing methods using machine learning either requires initial user behaviour data, or converges far too slowly. This method does not require any initial data on the PEV owner’s driving behaviour and shows improvement on learning speed. A combination of both model-based and model-free learning called Dyna-Q algorithm is utilized. Every time a real experience is obtained, the model is updated and the RL agent will learn from both real data set and “imagined” experience from the model. Due to the vast amount of state space, a table-look up method is impractical and a value approximation method using deep neural networks is employed for estimating the long-term expected reward of all state-action pairs. An average of historical price is used to predict future price. Three different user behaviour without any initial PEV owner behaviour data are simulated. A purely model-free DQN method is shown to run out of battery during trips very often, and is impractical for real life charging scenarios. Simulation results demonstrate the effectiveness of the proposed approach and its ability to reach an optimal policy quicker while avoiding state of charge (SOC) depleting during trips when compared to existing PEV charging schemes for all three different users profiles.

show abstract

“…[26]. Donadee et al [27] used stochastic models of (i) plug-in and plug-out behavior, (ii) energy required for transportation, and (iii) electric energy prices. These stochastic models were incorporated into an infinite-horizon Markov decision process (MDP) to minimize the sum of electric energy charging costs, driving costs, and the cost of any driver inconvenience.…”

Section: Literature Reviewmentioning

confidence: 99%

Stochastic control of smart home energy management with plug-in electric vehicle battery energy storage and photovoltaic array

Moura

et al. 2016

Journal of Power Sources

313

127

View full text Add to dashboard Cite

Newcastle University ePrints -eprint.ncl.ac.uk Wu X, Hu X, Moura S, Yin X, Pickert V. Stochastic control of smart home energy management with plug-in electric vehicle battery energy storage and photovoltaic array. AbstractEnergy management strategies are instrumental in the performance and economy of smart homes integrating renewable energy and energy storage. This article focuses on stochastic energy management of a smart home with PEV (plug-in electric vehicle) energy storage and photovoltaic (PV) array. It is motivated by the challenges associated with sustainable energy supplies and the local energy storage opportunity provided by vehicle electrification. This paper seeks to minimize a consumer's energy charges under a time-of-use tariff, while satisfying home power demand and PEV charging requirements, and accommodating the variability of solar power. First, the randomvariable models are developed, including Markov Chain model of PEV mobility, as well as predictive models of home power demand and PV power supply. Second, a stochastic optimal control problem is mathematically formulated for managing the power flow among energy sources in the smart home. Finally, based on time-varying electricity price, we systematically examine the performance of the proposed control strategy. As a result, the electric cost is 493.6% less for a Tesla Model S with optimal stochastic dynamic programming (SDP) control relative to the no optimal control case, and it is by 175.89% for a Nissan Leaf.

show abstract

Optimal Autonomous Charging of Electric Vehicles with Stochastic Driver Behavior

Cited by 15 publications

References 12 publications

Optimal Operation of Interdependent Power Systems and Electrified Transportation Networks

Optimal Operation of Interdependent Power Systems and Electrified Transportation Networks

Autonomous PEV Charging Scheduling Using Deep-Q Network and Dyna-Q Reinforcement Learning

Stochastic control of smart home energy management with plug-in electric vehicle battery energy storage and photovoltaic array

Contact Info

Product

Resources

About