Shared autonomous electric vehicle design and operations under uncertainties: a reliability-based design optimization approach

Lee, Ungki; Kang, Namwoo; Lee, Ikjin

doi:10.1007/s00158-019-02434-0

Cited by 22 publications

(12 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They demonstrated that highspeed charging and long-range EVs are better options than shorter ranges and slow-charging vehicles. Lee et al considered the uncertainties in SAEV systems and introduced reliability-based design optimization to derive an optimal SAEV system design that minimizes the total cost while satisfying the target reliability of the customer's wait time [15]. Melendez et al proposed a cyber-physical system (CPS) comprising a large fleet of SAEVs and a set of charging hubs for optimal planning and real-time operations [28].…”

Section: Saev System Optimizationmentioning

confidence: 99%

“…In addition, EVs help reduce fuel consumption and produce less environmental pollutants and greenhouse gas emissions [7][8][9][10]. Consequently, several studies related to operation and optimization of SAEV systems were conducted on the basis of SAEV simulations [1,[11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

“…A primary issue regarding SAEV operation is the behavior or movement of idle vehicles. Most SAEV studies randomly selected moving strategies or implemented free-floating systems where the vehicles park at the current location or at a designated parking spot [15][16][17][18][19]. However, during practical SAEV operation, parking in the middle of the road is unrealistic.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization

Kim

Lee

et al. 2022

Journal of Cleaner Production

Self Cite

View full text Add to dashboard Cite

Section: Saev System Optimizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization

Kim

Lee

et al. 2022

Journal of Cleaner Production

Self Cite

View full text Add to dashboard Cite

“…For example, [22] looks to choose the best location for charge stations out of a set of candidates by solving a MIP model that minimizes the cost of constructing charge stations subject to coverage constraints. Similarly, [23] chooses charge station locations from a set of candidates by solving a p-median problem minimizing the average distance from nodes in the map to charge stations.…”

Section: Literature Reviewmentioning

confidence: 99%

Real time operation of high-capacity electric vehicle ridesharing fleets

Zalesak

Samaranayake

2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…Reliability-based design optimization (RBDO) aims to minimize the objective function of a system while satisfying the probabilistic constraints and has been applied to a wide range of research fields such as structural analysis (Acar and Haftka 2007;Lee et al 2011;Choi et al 2015), vehicle design Grujicic et al 2010;Zhu et al 2015;Lee et al 2019), aerospace design (Frangopol and Maute 2003;Allen and Maute 2004;Bhattacharjee et al 2012;Nam and Mavris 2018), and vehicle system operation (Lee et al 2020). Under uncertainty of design variables Responsible Editor: Pingfeng Wang and parameters, reliability analysis evaluates a probabilistic constraint by predicting the probability of failure of a performance function.…”

Section: Introductionmentioning

confidence: 99%

Efficient sampling-based inverse reliability analysis combining Monte Carlo simulation (MCS) and feedforward neural network (FNN)

Lee

2021

Struct Multidisc Optim

Self Cite

View full text Add to dashboard Cite

Inverse reliability analysis evaluates a percentile value of a performance function when the target reliability is given. In cases of high dimensional or highly nonlinear performance functions, sampling-based methods such as Monte Carlo simulation (MCS), Latin hypercube sampling, and importance sampling are considered to be better candidates for reliability analysis. The sampling-based methods are very accurate but require a large number of samples, which can be very time-consuming. Therefore, this paper proposes an efficient and/or accurate sampling-based reliability analysis method without using a surrogate model. The proposed method helps to improve the accuracy of reliability analysis with the same number of samples or to ensure the same accuracy of reliability analysis with fewer samples. This study starts with an idea of training relationship between limited samples constituting realization of the performance distribution-usually between 10 and 100-and its corresponding true percentile value where the performance distribution is defined as a one-dimensional distribution resulted from a performance function and its random variables. To this end, feedforward neural network (FNN), which is one of promising artificial neural network (ANN) models that approximate high dimensional models using layered structures, is introduced in this study, and limited samples constituting realizations of various performance distributions and their corresponding true percentile values are used as input and target data, respectively. Various beta distributions are used to create the training data sets. A FNN training method using kernel density estimation and equidistant points to represent the kernel distribution data is also proposed to remove dimensionality of the training inputs. Comparative study shows that the proposed method training FNN with samples constituting realization of the performance distribution (Method 2) is more accurate than a method that directly estimates the percentile value from the kernel distribution fitting the samples constituting realization generated through MCS (Method 1). In addition, compared to Method 2, another proposed method that trains FNN with the kernel density estimation and equidistant points (Method 3) is more accurate in reliability analysis and more computationally efficient in FNN training. Method 3 is also applicable to high reliability problems, and it is more accurate than Kriging-based method for high dimensional problems.

show abstract

Shared autonomous electric vehicle design and operations under uncertainties: a reliability-based design optimization approach

Cited by 22 publications

References 42 publications

Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization

Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization

Real time operation of high-capacity electric vehicle ridesharing fleets

Efficient sampling-based inverse reliability analysis combining Monte Carlo simulation (MCS) and feedforward neural network (FNN)

Contact Info

Product

Resources

About