A Path-Aware Scheduler for Air-to-Ground Multipath Multimedia Delivery in Real Time

Machumilane, Achilles; Gotta, Alberto; Cassarà, Pietro; Bacco, Manlio

doi:10.1109/mcom.001.2100904

Cited by 6 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since connectivity with the satellite requires the LOS, we assume successful traffic reception only if there is LOS. We assume that the AC agent receives some feedback reports as in [3], indicating the reception status and, consequently, recording the link state.…”

Section: System Modelmentioning

confidence: 99%

“…This paper proposes an RL-based agent to self-learn link selection in non-terrestrial networks with Multi-Path Routing (MPR) in dense urban scenarios. MPR allows a UE with multiple radios to set up multiple satellite connections to improve reliability and data rate [3], [4] even when the performance of the single link is degraded in terms of LOS. We assume a non-stationary LOS probability due to the continuous variation of the satellite elevation angle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach

Machumilane,

Gotta,

Cassará

et al. 2023

ICC 2023 - IEEE International Conference on Communications

Self Cite

View full text Add to dashboard Cite

In Non-Terrestrial Networks (NTNs), where LEO satellites and User Equipment (UE) move relative to each other, Line-of-Sight (LOS) tracking,and adapting to channel state variations due to endpoint movements are a major challenge. Therefore, continuous LOS estimation and channel impairment compensation are crucial for a UE to access a satellite and maintain connectivity. In this paper, we propose a Actor-Critic (AC)-Reinforcement Learning (RL) framework for traffic scheduling in NTN scenarios where the channel state is non-stationary due to the variability of LOS, which depends on the current satellite elevation. We deploy the framework as an agent in a Multi-Path Routing (MPR) scheme where the UE can access more than one satellite simultaneously to improve link reliability and throughput. We study how the agent schedules traffic on multiple satellite links by adopting the AC version of RL. The agent continuously trains based on variations in satellite elevation angles, handoffs, and relative LOS probabilities. We compare the agent retraining time with the satellite visibility intervals to investigate the effectiveness of the agent's learning rate. We carry out performance analysis considering the dense urban area of Chicago, where high-rise buildings significantly affect the LOS. The simulation results show how the learning agent selects the scheduling policy when it is connected to a pair of satellites. The results also show that the retraining time of the learning agent is up to 0.1 times the satellite visibility time at certain elevations, which guarantees efficient use of satellite visibility.

show abstract

Section: System Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach

Machumilane,

Gotta,

Cassará

et al. 2023

ICC 2023 - IEEE International Conference on Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…The generative models learned the latent space and distributions of the training data, allowing them to produce synthetic traces with similar statistical characteristics to the original dataset. Alternatively, without access to a channel model, the training data could be obtained from traces acquired through real-time transmissions using feedback mechanisms, as demonstrated in [11]…”

Section: Channel Modelmentioning

confidence: 99%

Federated Semi-Supervised Classification of Multimedia Flows for 3D Networks

Bano

Machumilane

Valerio

et al. 2022

2022 IEEE 21st Mediterranean Electrotechnical Conference (MELECON)

View full text Add to dashboard Cite

Automatic traffic classification is increasingly becoming important in traffic engineering, as the current trend of encrypting transport information (e.g., behind HTTP-encrypted tunnels) prevents intermediate nodes from accessing end-toend packet headers. However, this information is crucial for traffic shaping, network slicing, and Quality of Service (QoS) management, for preventing network intrusion, and for anomaly detection. 3D networks offer multiple routes that can guarantee different levels of QoS. Therefore, service classification and separation are essential to guarantee the required QoS level to each traffic sub-flow through the appropriate network trunk. In this paper, a federated feature selection and feature reduction learning scheme is proposed to classify network traffic in a semisupervised cooperative manner. The federated gateways of 3D network help to enhance the global knowledge of network traffic to improve the accuracy of anomaly and intrusion detection and service identification of a new traffic flow.

show abstract

“…This paper proposes a Reinforcement Learning (RL)-based network function (NF) to self-learn the selection of non-terrestrial links with Multi-Path Routing (MPR) in dense urban scenarios. In an MPR transmission system, an original data stream is split into sub-streams, each of which is transmitted over its own path [3]. This means that the transmission system is characterized by multiple spatially or logically separated paths that are aggregated for transmission [2].…”

Section: Introductionmentioning

confidence: 99%

“…Multipath transmission can support UAVs deployed in satellite networks when there is no LOS [4]. In our scenario, the MPR allows UE with multiple radios to set up multiple satellite links to improve reliability and data rates [3,4] even when the performance of a single link is degraded due to LOS variations. Despite all these advantages of multipath transmission, dynamic path selection and estimating the required replicas for traffic protection are major challenges and require the Channel State Information (CSI).…”

Section: Introductionmentioning

confidence: 99%

Learning-Based Traffic Scheduling in Non-Stationary Multipath 5G Non-Terrestrial Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

In non-terrestrial networks, where low Earth orbit satellites and user equipment move relative to each other, line-of-sight tracking and adapting to channel state variations due to endpoint movements are a major challenge. Therefore, continuous line-of-sight estimation and channel impairment compensation are crucial for user equipment to access a satellite and maintain connectivity. In this paper, we propose a framework based on actor-critic reinforcement learning for traffic scheduling in non-terrestrial networks scenario where the channel state is non-stationary due to the variability of the line of sight, which depends on the current satellite elevation. We deploy the framework as an agent in a multipath routing scheme where the user equipment can access more than one satellite simultaneously to improve link reliability and throughput. We investigate how the agent schedules traffic in multiple satellite links by adopting policies that are evaluated by an actor-critic reinforcement learning approach. The agent continuously trains its model based on variations in satellite elevation angles, handovers, and relative line-of-sight probabilities. We compare the agent’s retraining time with the satellite visibility intervals to investigate the effectiveness of the agent’s learning rate. We carry out performance analysis while considering the dense urban area of Paris, where high-rise buildings significantly affect the line of sight. The simulation results show how the learning agent selects the scheduling policy when it is connected to a pair of satellites. The results also show that the retraining time of the learning agent is up to 0.1times the satellite visibility time at given elevations, which guarantees efficient use of satellite visibility.

show abstract

A Path-Aware Scheduler for Air-to-Ground Multipath Multimedia Delivery in Real Time

Cited by 6 publications

References 12 publications

Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach

Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach

Federated Semi-Supervised Classification of Multimedia Flows for 3D Networks

Learning-Based Traffic Scheduling in Non-Stationary Multipath 5G Non-Terrestrial Networks

Contact Info

Product

Resources

About