Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362632765> ?p ?o ?g. }
- W4362632765 endingPage "1233" @default.
- W4362632765 startingPage "1218" @default.
- W4362632765 abstract "Given the uncertainty of orders and the dynamically changing workload of charging stations, how to dispatch and charge electric vehicle (EV) fleets becomes a significant challenge facing e-hailing platforms. The common practice is to dispatch EVs to serve orders by heuristic matching methods but enable EV drivers to independently make charging decisions based on their experiences, which may compromise the platform’s performance. This study proposes a Markov decision process to jointly optimize the charging and order-dispatching schemes for an e-hailing EV fleet, which provides pick-up services for passengers only from a designated transportation hub (i.e., no pick-up from different locations). The objective is to maximize the total revenue of the fleet throughout a finite horizon. The complete state transition equations of the EV fleet are formulated to track the state-of-charge of their batteries. To learn the charging and order-dispatching policy in a dynamic stochastic environment, an online approximation algorithm is developed, which integrates the model-based reinforcement learning (RL) framework with a novel SARSA(Δ)-sample average approximation (SAA) architecture. Compared with the model-free RL algorithm and approximation dynamic programming (ADP), our algorithm explores high-quality decisions by an SAA model with empirical state transitions and exploits the best decisions so far by an SARSA(Δ) sample-trajectory updating. Computational results based on a real case show that, compared with the existing heuristic method and the ADP in the literature, the proposed approach increases the daily revenue by an average of 31.76% and 14.22%, respectively." @default.
- W4362632765 created "2023-04-07" @default.
- W4362632765 creator A5010523153 @default.
- W4362632765 creator A5028809711 @default.
- W4362632765 creator A5067974546 @default.
- W4362632765 creator A5079049099 @default.
- W4362632765 date "2023-11-01" @default.
- W4362632765 modified "2023-10-15" @default.
- W4362632765 title "An online reinforcement learning approach to charging and order-dispatching optimization for an e-hailing electric vehicle fleet" @default.
- W4362632765 cites W1489720431 @default.
- W4362632765 cites W1507985183 @default.
- W4362632765 cites W2043341809 @default.
- W4362632765 cites W2070423620 @default.
- W4362632765 cites W2074780355 @default.
- W4362632765 cites W2091839368 @default.
- W4362632765 cites W2094533500 @default.
- W4362632765 cites W2147107304 @default.
- W4362632765 cites W2147118779 @default.
- W4362632765 cites W2156973359 @default.
- W4362632765 cites W2294947825 @default.
- W4362632765 cites W2336603544 @default.
- W4362632765 cites W2416108505 @default.
- W4362632765 cites W2508168463 @default.
- W4362632765 cites W2618568670 @default.
- W4362632765 cites W2623725210 @default.
- W4362632765 cites W2760724745 @default.
- W4362632765 cites W2770275145 @default.
- W4362632765 cites W2810335761 @default.
- W4362632765 cites W2900428661 @default.
- W4362632765 cites W2908955769 @default.
- W4362632765 cites W2921638490 @default.
- W4362632765 cites W2943316743 @default.
- W4362632765 cites W2966930497 @default.
- W4362632765 cites W2967477084 @default.
- W4362632765 cites W3002585184 @default.
- W4362632765 cites W3020907443 @default.
- W4362632765 cites W3037451795 @default.
- W4362632765 cites W3048236545 @default.
- W4362632765 cites W3104599887 @default.
- W4362632765 cites W3137633810 @default.
- W4362632765 cites W3179035369 @default.
- W4362632765 cites W3183630332 @default.
- W4362632765 cites W4205514306 @default.
- W4362632765 cites W4221162600 @default.
- W4362632765 cites W4241918052 @default.
- W4362632765 cites W4308195387 @default.
- W4362632765 doi "https://doi.org/10.1016/j.ejor.2023.03.039" @default.
- W4362632765 hasPublicationYear "2023" @default.
- W4362632765 type Work @default.
- W4362632765 citedByCount "1" @default.
- W4362632765 countsByYear W43626327652023 @default.
- W4362632765 crossrefType "journal-article" @default.
- W4362632765 hasAuthorship W4362632765A5010523153 @default.
- W4362632765 hasAuthorship W4362632765A5028809711 @default.
- W4362632765 hasAuthorship W4362632765A5067974546 @default.
- W4362632765 hasAuthorship W4362632765A5079049099 @default.
- W4362632765 hasConcept C10138342 @default.
- W4362632765 hasConcept C105795698 @default.
- W4362632765 hasConcept C106189395 @default.
- W4362632765 hasConcept C111919701 @default.
- W4362632765 hasConcept C11413529 @default.
- W4362632765 hasConcept C121332964 @default.
- W4362632765 hasConcept C121955636 @default.
- W4362632765 hasConcept C126255220 @default.
- W4362632765 hasConcept C127413603 @default.
- W4362632765 hasConcept C1276947 @default.
- W4362632765 hasConcept C13662910 @default.
- W4362632765 hasConcept C137631369 @default.
- W4362632765 hasConcept C154945302 @default.
- W4362632765 hasConcept C159886148 @default.
- W4362632765 hasConcept C162324750 @default.
- W4362632765 hasConcept C163258240 @default.
- W4362632765 hasConcept C165064840 @default.
- W4362632765 hasConcept C173801870 @default.
- W4362632765 hasConcept C182306322 @default.
- W4362632765 hasConcept C195487862 @default.
- W4362632765 hasConcept C2776422217 @default.
- W4362632765 hasConcept C2777305159 @default.
- W4362632765 hasConcept C2778476105 @default.
- W4362632765 hasConcept C30600047 @default.
- W4362632765 hasConcept C33923547 @default.
- W4362632765 hasConcept C37404715 @default.
- W4362632765 hasConcept C41008148 @default.
- W4362632765 hasConcept C42475967 @default.
- W4362632765 hasConcept C62520636 @default.
- W4362632765 hasConcept C76155785 @default.
- W4362632765 hasConcept C97541855 @default.
- W4362632765 hasConceptScore W4362632765C10138342 @default.
- W4362632765 hasConceptScore W4362632765C105795698 @default.
- W4362632765 hasConceptScore W4362632765C106189395 @default.
- W4362632765 hasConceptScore W4362632765C111919701 @default.
- W4362632765 hasConceptScore W4362632765C11413529 @default.
- W4362632765 hasConceptScore W4362632765C121332964 @default.
- W4362632765 hasConceptScore W4362632765C121955636 @default.
- W4362632765 hasConceptScore W4362632765C126255220 @default.
- W4362632765 hasConceptScore W4362632765C127413603 @default.
- W4362632765 hasConceptScore W4362632765C1276947 @default.
- W4362632765 hasConceptScore W4362632765C13662910 @default.