Multiple agents and reinforcement learning for modelling charging loads of electric taxis

Jiang, Changxu; Jing, Zhaoxia; Cui, Xueshen; Ji, Tianyao; Wu, Q. H.

doi:10.1016/j.apenergy.2018.03.164

Cited by 41 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may lead to concluding that they were not that crucial in deducing the best actions to achieve the objectives of the methods presented in these papers to control the energy distribution system costs. TOU, on the other hand, appeared in several published research work ( [89], [90], [91], [92], [93], [82], [94], [66], [95], and [63]) as a state parameter, but not as frequent as the charging or discharging cost. • Base load, charging demand, consmption at road, charging station demand, battery SOC, waiting time, driving time, charging efficiency, location, distance, road velocity, direction, waiting cost, charge/discharge cost, charging rate, transformer loading, reewable energy, storage, TOU prices, V2G.…”

Section: Inputsmentioning

confidence: 99%

Reinforcement Learning Based EV Charging Management Systems–A Review

2021

View full text Add to dashboard Cite

To mitigate global warming and energy shortage, integration of renewable energy generation sources, energy storage systems, and plug-in electric vehicles (PEVs) have been introduced in recent years. The application of electric vehicles (EV) in the smart grid has shown a significant option to reduce carbon emission. However, due to the limited battery capacity, managing the charging and discharging process of EV as a distributed power supply is a challenging task. Moreover, the unpredictable nature of renewable energy generation, uncertainties of plug-in electric vehicles associated parameters, energy prices, and the time-varying load create new challenges for the researchers and industries to maintain a stable operation of the power system. The EV battery charging management system plays a main role in coordinating the charging and discharging mechanism to efficiently realize a secure, efficient, and reliable power system. More recently, there has been an increasing interest in data-driven approaches in EV charging modeling. Consequently, researchers are looking to deploy model-free approaches for solving the EV charging management with uncertainties. Among many existing model-free approaches, Reinforcement Learning (RL) has been widely used for EV charging management. Unlike other machine learning approaches, the RL technique is based on maximizing the cumulative reward. This paper reviews the existing literature related to the RL-based framework, objectives, and architecture for the charging coordination strategies of electric vehicles in the power systems. In addition, the review paper presents a detailed comparative analysis of the techniques used for achieving different charging coordination objectives while satisfying multiple constraints. This paper also focuses on the application of RL in EV coordination for research and development of the cutting-edge optimized energy management system (EMS), which are applicable for EV charging.

show abstract

Section: Inputsmentioning

confidence: 99%

Reinforcement Learning Based EV Charging Management Systems–A Review

2021

View full text Add to dashboard Cite

show abstract

“…The energy-management problem grows from a single vehicle to multiple vehicles in a connected environment. Furthermore, to build an accurate charging-load model for multiple plug-in electric taxis, the authors in [33] applied multiple agents and a multiple-step ( )-Q m learning algorithm to search for a precise and detailed charging strategy for those vehicles. The reward performance and convergence rate were verified to be much better.…”

Section: Hybrid Algorithmsmentioning

confidence: 99%

Reinforcement Learning for Hybrid and Plug-In Hybrid Electric Vehicle Energy Management: Recent Advances and Prospects

et al. 2019

EEE Ind. Electron. Mag.

190

View full text Add to dashboard Cite

E nergy management is a critical technology in plug-in hybrid-electric vehicles (PHEVs) for maximizing efficiency, fuel economy, and range, as well as reducing pollutant emissions. At the same time, deep reinforcement learning (DRL) has become an effective and important methodology to formulate model-free and realtime energy-management strategies for HEVs and PHEVs. In this article, we describe the energy-management issues of HEVs/PHEVs and summarize a variety of potential DRL applications for onboard energy management. We also discuss the prospects for various DRL approaches in the energy-management field.

show abstract

“…Foremost, several researchers have studied the load prediction of ETs, in order to evaluate the impact on the grid. Thus, the authors of [57] proposed a precise charging load model for ETs based on multi-step Q(λ) learning. In [58], the GPS measurements of 460 San Francisco taxis were used to estimate the charging load.…”

Section: Electric Taxis (Ets) Approachesmentioning

confidence: 99%

Electric Vehicles for Public Transportation in Power Systems: A Review of Methodologies

et al. 2019

View full text Add to dashboard Cite

The market for electric vehicles (EVs) has grown with each year, and EVs are considered to be a proper solution for the mitigation of urban pollution. So far, not much attention has been devoted to the use of EVs for public transportation, such as taxis and buses. However, a massive introduction of electric taxis (ETs) and electric buses (EBs) could generate issues in the grid. The challenges are different from those of private EVs, as their required load is much higher and the related time constraints must be considered with much more attention. These issues have begun to be studied within the last few years. This paper presents a review of the different approaches that have been proposed by various authors, to mitigate the impact of EBs and ETs on the future smart grid. Furthermore, some projects with regard to the integration of ETs and EBs around the world are presented. Some guidelines for future works are also proposed.

show abstract

Multiple agents and reinforcement learning for modelling charging loads of electric taxis

Cited by 41 publications

References 32 publications

Reinforcement Learning Based EV Charging Management Systems–A Review

Reinforcement Learning Based EV Charging Management Systems–A Review

Reinforcement Learning for Hybrid and Plug-In Hybrid Electric Vehicle Energy Management: Recent Advances and Prospects

Electric Vehicles for Public Transportation in Power Systems: A Review of Methodologies

Contact Info

Product

Resources

About