Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285024495> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4285024495 endingPage "111882" @default.
- W4285024495 startingPage "111882" @default.
- W4285024495 abstract "To meet the 2050 CO 2 targets, the shipping industry which is responsible for about 3% of global CO 2 emissions needs to be optimized in several aspects. Obviously, alternative fuels constitute the main measure in this respect. However, relatively high fuel prices in combination with increasing political and economic pressure may raise the need for more efficient ship operation. Ship route optimization can make an indispensable contribution to achieving this goal. In this sense, this paper applies an innovative approach for route optimization using Reinforcement Learning (RL). For this purpose, a generic ship model is first developed using Artificial Neural Networks (ANNs) to predict the fuel consumption of the ship. Moreover, various RL methods, namely Deep Q-Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO) are applied. The application of RL enables continuous action space and simultaneous optimization of ship speed and heading. DDPG demonstrates the best results as an off-policy and policy gradient method which allows a continuous action space. For example, in the fuel consumption minimization scenario without time limitation, this method can achieve savings of 6.64%. For DQN as a method with discrete action space, this value is 1.07%. • ANN models provide an accurate and realistic representation of the ship's fuel consumption. • Reinforcement learning enables continuous action space for route optimization. • DDPG proves to be the best option for ship route estimation with RL. • Compared to the reference conditions, fuel savings of up to 6.64% are achieved. • The advantages of continuous action space over discrete action space are confirmed." @default.
- W4285024495 created "2022-07-12" @default.
- W4285024495 creator A5003830974 @default.
- W4285024495 creator A5048356664 @default.
- W4285024495 creator A5073803624 @default.
- W4285024495 creator A5079490415 @default.
- W4285024495 creator A5079834570 @default.
- W4285024495 date "2022-09-01" @default.
- W4285024495 modified "2023-09-30" @default.
- W4285024495 title "Marine route optimization using reinforcement learning approach to reduce fuel consumption and consequently minimize CO2 emissions" @default.
- W4285024495 cites W1933995582 @default.
- W4285024495 cites W1975513190 @default.
- W4285024495 cites W2003946878 @default.
- W4285024495 cites W2012199273 @default.
- W4285024495 cites W2018903049 @default.
- W4285024495 cites W2058228054 @default.
- W4285024495 cites W2134634502 @default.
- W4285024495 cites W2137983211 @default.
- W4285024495 cites W2145339207 @default.
- W4285024495 cites W2169528473 @default.
- W4285024495 cites W2291124468 @default.
- W4285024495 cites W2320714508 @default.
- W4285024495 cites W2472729347 @default.
- W4285024495 cites W2490049290 @default.
- W4285024495 cites W2540040370 @default.
- W4285024495 cites W2563022518 @default.
- W4285024495 cites W2761633467 @default.
- W4285024495 cites W2788422172 @default.
- W4285024495 cites W2795761649 @default.
- W4285024495 cites W2799743150 @default.
- W4285024495 cites W2910427893 @default.
- W4285024495 cites W2915513980 @default.
- W4285024495 cites W2999082917 @default.
- W4285024495 cites W3009283923 @default.
- W4285024495 cites W3046981189 @default.
- W4285024495 cites W335734595 @default.
- W4285024495 doi "https://doi.org/10.1016/j.oceaneng.2022.111882" @default.
- W4285024495 hasPublicationYear "2022" @default.
- W4285024495 type Work @default.
- W4285024495 citedByCount "11" @default.
- W4285024495 countsByYear W42850244952022 @default.
- W4285024495 countsByYear W42850244952023 @default.
- W4285024495 crossrefType "journal-article" @default.
- W4285024495 hasAuthorship W4285024495A5003830974 @default.
- W4285024495 hasAuthorship W4285024495A5048356664 @default.
- W4285024495 hasAuthorship W4285024495A5073803624 @default.
- W4285024495 hasAuthorship W4285024495A5079490415 @default.
- W4285024495 hasAuthorship W4285024495A5079834570 @default.
- W4285024495 hasConcept C127413603 @default.
- W4285024495 hasConcept C144024400 @default.
- W4285024495 hasConcept C154945302 @default.
- W4285024495 hasConcept C171146098 @default.
- W4285024495 hasConcept C30772137 @default.
- W4285024495 hasConcept C36289849 @default.
- W4285024495 hasConcept C39432304 @default.
- W4285024495 hasConcept C41008148 @default.
- W4285024495 hasConcept C45882903 @default.
- W4285024495 hasConcept C66938386 @default.
- W4285024495 hasConcept C67203356 @default.
- W4285024495 hasConcept C97541855 @default.
- W4285024495 hasConceptScore W4285024495C127413603 @default.
- W4285024495 hasConceptScore W4285024495C144024400 @default.
- W4285024495 hasConceptScore W4285024495C154945302 @default.
- W4285024495 hasConceptScore W4285024495C171146098 @default.
- W4285024495 hasConceptScore W4285024495C30772137 @default.
- W4285024495 hasConceptScore W4285024495C36289849 @default.
- W4285024495 hasConceptScore W4285024495C39432304 @default.
- W4285024495 hasConceptScore W4285024495C41008148 @default.
- W4285024495 hasConceptScore W4285024495C45882903 @default.
- W4285024495 hasConceptScore W4285024495C66938386 @default.
- W4285024495 hasConceptScore W4285024495C67203356 @default.
- W4285024495 hasConceptScore W4285024495C97541855 @default.
- W4285024495 hasLocation W42850244951 @default.
- W4285024495 hasOpenAccess W4285024495 @default.
- W4285024495 hasPrimaryLocation W42850244951 @default.
- W4285024495 hasRelatedWork W1562959674 @default.
- W4285024495 hasRelatedWork W2899084033 @default.
- W4285024495 hasRelatedWork W2923653485 @default.
- W4285024495 hasRelatedWork W2952472710 @default.
- W4285024495 hasRelatedWork W3005560120 @default.
- W4285024495 hasRelatedWork W3037422413 @default.
- W4285024495 hasRelatedWork W4206669594 @default.
- W4285024495 hasRelatedWork W4210912933 @default.
- W4285024495 hasRelatedWork W4224287422 @default.
- W4285024495 hasRelatedWork W4255994452 @default.
- W4285024495 hasVolume "259" @default.
- W4285024495 isParatext "false" @default.
- W4285024495 isRetracted "false" @default.
- W4285024495 workType "article" @default.