Partially explainable big data driven deep reinforcement learning for green 5G UAV

Simple item page
dc.contributor.authorGuo, Weisi
dc.date.accessioned2021-08-20T12:00:54Z
dc.date.available2021-08-20T12:00:54Z
dc.date.issued2020-07-27
dc.description.abstractUAV enabled terrestrial wireless networks enables targeted user-centric service provisioning to en-richen both deep urban coverage and target various rural challenge areas. However, UAVs have to balance the energy consumption of flight with the benefits of wireless capacity delivery via a high dimensional optimisation problem. Classic reinforcement learning (RL) cannot meet this challenge and here, we propose to use deep reinforcement learning (DRL) to optimise both aggregate and minimum service provisioning. In order to achieve a trusted autonomy, the DRL agents have to be able to explain its actions for transparent human-machine interrogation. We design a Double Dueling Deep Q-learning Neural Network (DDDQN) with Prioritised Experience Replay (PER) and fixed Q-targets to achieve stable performance and avoid over-fitting, offering performance gains over naive DQN algorithms. We then use a big data driven case study and found that UAVs battery size determines the nature of its autonomous mission, ranging from an efficient exploiter of one hotspot (100% reward gain) to a stochastic explorer of many hotspots (60-150% reward gain). Using a variety of telecom and social media data, we infer driving Quality-of-Experience (QoE) and Quality-of-Service (QoS) metrics that are in contention with UAV power and communication constraints. Our greener UAVs (30-40% energy saved) address both quantitative QoS and qualitative QoE issues. Partial interpretability in the reinforcement learning is achieved using data features extracted in the hidden layers, offering an initial step for explainable AI (XAI) connecting machine intelligence with human expertise.en_UK
dc.identifier.citationGuo W. (2021) Partially explainable big data driven deep reinforcement learning for green 5G UAV. In: ICC 2020 - 2020 IEEE International Conference on Communications (ICC), 7-11 June 2020, Dublinen_UK
dc.identifier.issn1938-1883
dc.identifier.urihttps://doi.org/10.1109/ICC40277.2020.9149151
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17030
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectUAVen_UK
dc.subjectXAIen_UK
dc.subjectmachine learningen_UK
dc.subjectdeep reinforcement learningen_UK
dc.subjectradio resource managementen_UK
dc.subjectenergy efficiencyen_UK
dc.subjectbig dataen_UK
dc.titlePartially explainable big data driven deep reinforcement learning for green 5G UAVen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Partially_explainable_big_data_driven_deep_reinforcement_learning-2020.pdf
Size:
4.19 MB
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)