A service demand forecasting model for one-way electric car-sharing systems combining long short-term memory networks with Granger causality test

Wang, Ning; Guo, Jiahui; Liu, Xiang; Tong, Fang

doi:10.1016/j.jclepro.2019.118812

Cited by 35 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the loss value of the BP-DNN estimator remains higher. Further exploration will focus on the search for better deep Q-learning algorithms for improving the fit of goodness [55][56][57][58][59][60].…”

Section: Discussionmentioning

confidence: 99%

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

Wang

Guo

2021

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

The fusion of electricity, automation, and sharing is forming a new Autonomous Mobility-on-Demand (AMoD) system in current urban transportation, in which the Shared Autonomous Electric Vehicles (SAEVs) are a fleet to execute delivery, parking, recharging, and repositioning tasks automatically. To model the decision-making process of AMoD system and optimize multiaction dynamic dispatching of SAEVs over a long horizon, the dispatching problem of SAEVs is modeled according to Markov Decision Process (MDP) at first. Then two optimization models from short-sighted view and farsighted view based on combinatorial optimization theory are built, respectively. The former focuses on the instant and single-step reward, while the latter aims at the accumulative and multistep return. After that, the Kuhn–Munkres algorithm is set as the baseline method to solve the first model to achieve optimal multiaction allocation instructions for SAEVs, and the combination of deep Q-learning algorithm and Kuhn–Munkres algorithm is designed to solve the second model to realize the global optimization. Finally, a toy example, a macrosimulation of 1 month, and a microsimulation of 6 hours based on actual historical operation data are conducted. Results show that (1) the Kuhn–Munkres algorithm ensures the computational effectiveness in the large-scale real-time application of the AMoD system; (2) the second optimization model considering long-term return can decrease average user waiting time and achieve a 2.78% increase in total revenue compared with the first model; (3) and integrating combinatorial optimization theory with reinforcement learning theory is a perfect package for solving the multiaction dynamic dispatching problem of SAEVs.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

Wang

Guo

2021

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Three reasons motivate the VAR/VEC Granger causality. First, it provides a yardstick for treating all the variables endogenously (Wang et al, 2020; Benk & Gillman, 2020; Ghysels et al, ; Kin et al, 2020). Second, it helps to decompose the factors into short and long run perspectives, providing information on their dynamic interaction (Mazzarisi et al, 2020; Shao et al, 2020; Wimmer et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

Has knowledge improved economic growth? Evidence from Nigeria and South Africa

Shobande

Asongu

2021

Journal of Public Affairs

View full text Add to dashboard Cite

This study examines whether knowledge causes economic growth in Africa's two leading economies: Nigeria and South Africa. Using the Vector Autoregressive and Vector Error Correction approach, the findings show cointegration among the variables. The speed of convergence of the variables to their long-term mean values is relatively higher for South Africa than for Nigeria. In the short run, it is observed that knowledge unidirectionally Granger causes growth for Nigeria, whereas bidirectional causality is observed for South Africa. The higher correlation between knowledge and growth in South Africa reflects the success of greater investment in education. Nigeria must increase investment in education and modern infrastructure to converge to South Africa's growth trajectory. Moreover, for Nigeria, (i) knowledge unidirectionally Granger cause growth, (ii) evidence of bidirectional causality flow is apparent between trade, the economic incentive and growth and (iii) health unidirectionally Granger cause knowledge. As for South Africa: (i) there is bidirectional causality between knowledge, trade openness and growth, whereas investment and economic incentive, unidirectionally Granger causes growth, (ii) investment, trade openness and health unidirectionally Granger cause knowledge and (iii) economic incentive unidirectionally Granger cause trade openness. In conclusion, this paper argues that a transformed education system can provide the knowledge base essential for promoting and sustaining economic growth.

show abstract

“…EEC is hypothesized to be achieved by constructing a new estimation model by combining long-short term memory network (LSTM) and random forest (RF) based on the real-time operational parameters of the vehicle itself such as velocity, acceleration, soc, temperature, etc. ( Wang et al, 2019 ).…”

Section: Multi-task Dynamic Assigning Problem Of Saevsmentioning

confidence: 99%

“…To judge whether a region is oversupply or undersupply, the predicted trip demand will be compared with the current vehicle supply number. The related forecast work can refer to Wang et al (2019) . Therefore, the absent vehicles in undersupply and the residual vehicles in oversupply regions at each time period are known in this research.…”

Section: Multi-task Dynamic Assigning Problem Of Saevsmentioning

confidence: 99%

Multi-task dispatch of shared autonomous electric vehicles for Mobility-on-Demand services – combination of deep reinforcement learning and combinatorial optimization method

Wang¹,

Guo²

2022

Heliyon

Self Cite

View full text Add to dashboard Cite

A service demand forecasting model for one-way electric car-sharing systems combining long short-term memory networks with Granger causality test

Cited by 35 publications

References 26 publications

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

Has knowledge improved economic growth? Evidence from Nigeria and South Africa

Multi-task dispatch of shared autonomous electric vehicles for Mobility-on-Demand services – combination of deep reinforcement learning and combinatorial optimization method

Contact Info

Product

Resources

About