Demand and capacity balancing technology based on multi-agent reinforcement learning

Simple item page
dc.contributor.authorChen, Yutong
dc.contributor.authorXu, Yan
dc.contributor.authorHu, Minghua
dc.contributor.authorYang, Lei
dc.date.accessioned2022-01-18T14:24:21Z
dc.date.available2022-01-18T14:24:21Z
dc.date.issued2021-11-15
dc.description.abstractTo effectively solve Demand and Capacity Balancing (DCB) in large-scale and high-density scenarios through the Ground Delay Program (GDP) in the pre-tactical stage, a sequential decision-making framework based on a time window is proposed. On this basis, the problem is transformed into Markov Decision Process (MDP) based on local observation, and then Multi-Agent Reinforcement Learning (MARL) method is adopted. Each flight is regarded as an independent agent to decide whether to implement GDP according to its local state observation. By designing the reward function in multiple combinations, a Mixed Competition and Cooperation (MCC) mode considering fairness is formed among agents. To improve the efficiency of MARL, we use the double Q-Learning Network (DQN), experience replay technology, adaptive ϵ-greedy strategy and Decentralized Training with Decentralized Execution (DTDE) framework. The experimental results show that the training process of the MARL method is convergent, efficient and stable. Compared with the Computer-Assisted Slot Allocation (CASA) method used in the actual operation, the number of flight delays and the average delay time is reduced by 33.7% and 36.7% respectively.en_UK
dc.identifier.citationChen Y, Xu Y, Hu M, Yang L (2021) Demand and capacity balancing technology based on multi-agent reinforcement learning. In: 2021 AIAA/IEEE 40th Digital Avionics Systems Conference (DASC), 3-7 October 2021, San Antonio, USAen_UK
dc.identifier.eisbn978-1-6654-3420-1
dc.identifier.issn2155-7209
dc.identifier.urihttps://doi.org/10.1109/DASC52595.2021.9594343
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17428
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectdemand and capacity balancingen_UK
dc.subjectground delay programen_UK
dc.subjectmulti-agent reinforcement learningen_UK
dc.subjectdouble Q-learning networken_UK
dc.subjectexperience replayen_UK
dc.subjectadaptive ϵ-greedy strategyen_UK
dc.subjectdecentralized training with decentralized executionen_UK
dc.titleDemand and capacity balancing technology based on multi-agent reinforcement learningen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Demand_and_capacity_balancing_technology-2021.pdf
Size:
820.83 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)