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

Kim, Seongsin; Lee, Ungki; Lee, Ikjin; Kang, Namwoo

doi:10.1016/j.jclepro.2021.130055

Cited by 24 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the customer-vehicle matching, there is also the pricing and dispatching decisions (Haliem et al 2021), which refers to the use of directing drivers to the areas with the highest demand. Hence, for instance, Kim et al (2022) propose the use of reinforced learning for shared autonomous electric vehicles. Notice, however, that the described articles refer either to simulation or to optimization approaches, but there is a lack of studies combining both.…”

Section: Related Work On Ridesharing Problemsmentioning

confidence: 99%

Combining Survival Analysis and Simheuristics to Predict the Risk of Delays in Urban Ridesharing Operations with Random Travel Times

Herrera

Panadero

Juan³

et al. 2022

2022 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

More sustainable transportation and mobility concepts, such as ridesharing, are gaining momentum in modern smart cities. In many real-life scenarios, travel times among potential customers' locations should be modeled as random variables. This uncertainty makes it difficult to design efficient ridesharing schedules and routing plans, since the risk of possible delays has to be considered as well. In this paper, we model ridesharing as a stochastic team orienteering problem in which the trade-off between maximizing the expected reward and the risk of incurring time delays is analyzed. In order to do so, we propose a simulation-optimization approach that combines a simheuristic algorithm with survival analysis techniques. The aforementioned methodology allows us to generate not only the probability that a given routing plan will suffer a delay, but also gives us the probability that the routing plan experiences delays of different sizes.

show abstract

Section: Related Work On Ridesharing Problemsmentioning

confidence: 99%

Combining Survival Analysis and Simheuristics to Predict the Risk of Delays in Urban Ridesharing Operations with Random Travel Times

Herrera

Panadero

Juan³

et al. 2022

2022 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

show abstract

“…The popular preference is using electromobility vehicles under sheared autonomous usage. For this reason, deep learning tools and optimization algorithms are seriously performed to obtain the most optimized system under various traffic conditions [6]. Janiaud et al [7] studied the electric powertrain simulation developed under Matlab-Simulink, intending to optimize performances and powertrain efficiency.…”

Section: Introductionmentioning

confidence: 99%

Suspension system design for pedal-assisted cargo E-quadricycle

Genç

2024

International Journal of Automotive Engineering and Technologies

View full text Add to dashboard Cite

Electro Micro-Mobility (EMM) has widely increased in Today‘s transportation preferences. The suspension system design based on the road profile in E-Quadricycle needs further investigation to present more optimized EMM vehicles soon. In this study, the pedal-assisted Cargo E-Quadricycle is investigated based on powertrain system modeling considering suspension system design. System modeling is applied to have an optimized suspension system design specified for Cargo E-Quadricycle to provide more comfortable driving. To achieve these targets, one-dimensional physical modeling is obtained, and the key parameters for system design are defined based on the State-space system modeling definition. In the next phase, the suspension system is constructed as a passive-controlled type with assigned suspension parameters considering natural frequency to provide driving comfort in urban transportation. Because four-wheeler Pedal-Assisted Cargo E-Quadricycles have specific vehicle kinematics and dynamics based on their own limited acceleration system and vehicle design, this study presents the suspension system design steps and remarkable dynamic concerns.

show abstract

“…A deep learning model-based solution for relocating and utilizing taxi data is developed to determine the best service system. The suggested strategy can significantly lower operating costs and on-demand service times [17]. Yi et al [18] proposed a model for electric vehicle demand prediction that acquired acceptable accuracy.…”

Section: Introductionmentioning

confidence: 99%

Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

Chatterjee¹,

Byun²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features. Electric kickboards are gradually growing in popularity in tourist and education-centric localities. In the upcoming arrival of electric kickboard vehicles, deploying a customer rental service is essential. Due to its freefloating nature, the shared electric kickboard is a common and practical means of transportation. Relocation plans for shared electric kickboards are required to increase the quality of service, and forecasting demand for their use in a specific region is crucial. Predicting demand accurately with small data is troublesome. Extensive data is necessary for training machine learning algorithms for effective prediction. Data generation is a method for expanding the amount of data that will be further accessible for training. In this work, we proposed a model that takes time-series customers' electric kickboard demand data as input, pre-processes it, and generates synthetic data according to the original data distribution using generative adversarial networks (GAN). The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data. We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results. We modified The Wasserstein GAN-gradient penalty (GP) with the RMSprop optimizer and then employed Spectral Normalization (SN) to improve training stability and faster convergence. Finally, we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction. We used various evaluation criteria and visual representations to compare our proposed model's performance. Synthetic data generated by our suggested GAN model is also evaluated. The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem, and it also converges faster than previous GAN models for synthetic data creation. The presented model's performance is compared to existing ensemble and baseline models. The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error (MAPE) of 4.476 and increase prediction accuracy.

show abstract

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

Cited by 24 publications

References 36 publications

Combining Survival Analysis and Simheuristics to Predict the Risk of Delays in Urban Ridesharing Operations with Random Travel Times

Combining Survival Analysis and Simheuristics to Predict the Risk of Delays in Urban Ridesharing Operations with Random Travel Times

Suspension system design for pedal-assisted cargo E-quadricycle

Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

Contact Info

Product

Resources

About