Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity
We consider multipath TCP (MPTCP) flows over the data networking dynamics of IEEE 802.11<i>ay</i> for drone surveillance of areas using high-definition video streaming. Mobility-induced handoffs are critical in IEEE 802.11<i>ay</i> (because of the smaller coverage of mmWaves)...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Drones |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-446X/7/1/30 |
_version_ | 1797443667897614336 |
---|---|
author | Shiva Raj Pokhrel Michel Mandjes |
author_facet | Shiva Raj Pokhrel Michel Mandjes |
author_sort | Shiva Raj Pokhrel |
collection | DOAJ |
description | We consider multipath TCP (MPTCP) flows over the data networking dynamics of IEEE 802.11<i>ay</i> for drone surveillance of areas using high-definition video streaming. Mobility-induced handoffs are critical in IEEE 802.11<i>ay</i> (because of the smaller coverage of mmWaves), which adversely affects the performance of such data streaming flows. As a result of the enhanced 802.11<i>ay</i> network events and features (triggered by beamforming, channel bonding, MIMO, mobility-induced handoffs, channel sharing, retransmissions, etc.), the time taken for packets to travel end-to-end in 802.11<i>ay</i> are inherently time-varying. Several fundamental assumptions inherent in stochastic TCP models, including Poisson arrivals of packets, Gaussian process, and parameter certainty, are challenged by the improved data traffic dynamics over IEEE 802.11<i>ay</i> networks. The MPTCP model’s state estimation differs largely from the actual network values. We develop a new <i>data-driven stochastic framework</i> to address current deficiencies of MPTCP models and design a foundational architecture for intelligent multipath scheduling (at the <i>transport layer</i>) considering lower layer (hybrid) beamforming. At the heart of our cross-layer architecture is an intelligent learning agent for actuating and interfacing, which learns from experience optimal packet cloning, scheduling, aggregation, and beamforming using successful features of multi-armed bandits and federated learning. We demonstrate that the proposed framework can estimate and optimize jointly (<b>explore–exploit</b>) and is more practicable for designing the next generation of low-delay and robust MPTCP models. |
first_indexed | 2024-03-09T13:00:20Z |
format | Article |
id | doaj.art-f861887a4b8b4c7c8725c28b5ae743a4 |
institution | Directory Open Access Journal |
issn | 2504-446X |
language | English |
last_indexed | 2024-03-09T13:00:20Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Drones |
spelling | doaj.art-f861887a4b8b4c7c8725c28b5ae743a42023-11-30T21:55:18ZengMDPI AGDrones2504-446X2022-12-01713010.3390/drones7010030Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless ConnectivityShiva Raj Pokhrel0Michel Mandjes1School of Information Technology, Deakin University, Geelong, VIC 3220, AustraliaFaculty of Science, Mathematics and Informatics Korteweg-de Vries Institute, University of Amsterdam, 1090 GE Amsterdam, The NetherlandsWe consider multipath TCP (MPTCP) flows over the data networking dynamics of IEEE 802.11<i>ay</i> for drone surveillance of areas using high-definition video streaming. Mobility-induced handoffs are critical in IEEE 802.11<i>ay</i> (because of the smaller coverage of mmWaves), which adversely affects the performance of such data streaming flows. As a result of the enhanced 802.11<i>ay</i> network events and features (triggered by beamforming, channel bonding, MIMO, mobility-induced handoffs, channel sharing, retransmissions, etc.), the time taken for packets to travel end-to-end in 802.11<i>ay</i> are inherently time-varying. Several fundamental assumptions inherent in stochastic TCP models, including Poisson arrivals of packets, Gaussian process, and parameter certainty, are challenged by the improved data traffic dynamics over IEEE 802.11<i>ay</i> networks. The MPTCP model’s state estimation differs largely from the actual network values. We develop a new <i>data-driven stochastic framework</i> to address current deficiencies of MPTCP models and design a foundational architecture for intelligent multipath scheduling (at the <i>transport layer</i>) considering lower layer (hybrid) beamforming. At the heart of our cross-layer architecture is an intelligent learning agent for actuating and interfacing, which learns from experience optimal packet cloning, scheduling, aggregation, and beamforming using successful features of multi-armed bandits and federated learning. We demonstrate that the proposed framework can estimate and optimize jointly (<b>explore–exploit</b>) and is more practicable for designing the next generation of low-delay and robust MPTCP models.https://www.mdpi.com/2504-446X/7/1/30internet of drones (IoD)multi-armed bandits (MAB)multipath TCP (MPTCP)schedulingbeamformingcross-layer approach |
spellingShingle | Shiva Raj Pokhrel Michel Mandjes Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity Drones internet of drones (IoD) multi-armed bandits (MAB) multipath TCP (MPTCP) scheduling beamforming cross-layer approach |
title | Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity |
title_full | Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity |
title_fullStr | Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity |
title_full_unstemmed | Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity |
title_short | Internet of Drones: Improving Multipath TCP over WiFi with Federated Multi-Armed Bandits for Limitless Connectivity |
title_sort | internet of drones improving multipath tcp over wifi with federated multi armed bandits for limitless connectivity |
topic | internet of drones (IoD) multi-armed bandits (MAB) multipath TCP (MPTCP) scheduling beamforming cross-layer approach |
url | https://www.mdpi.com/2504-446X/7/1/30 |
work_keys_str_mv | AT shivarajpokhrel internetofdronesimprovingmultipathtcpoverwifiwithfederatedmultiarmedbanditsforlimitlessconnectivity AT michelmandjes internetofdronesimprovingmultipathtcpoverwifiwithfederatedmultiarmedbanditsforlimitlessconnectivity |