2 results
Filters
Settings
Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , In-network Round-Trip Time estimation for TCP flows(2023); Transmission Control Protocol (TCP)’s tendency to fill up buffers in the network results in long standing queues. Active Queue Management (AQM) tries to solve this issue but typically requires manual tuning as the optimal parameters depend on the Round-Trip Time (RTT) of the flow, which is unknown to the AQM. In this paper, we use network simulation and supervised learning to train a neural network to infer the RTT of a TCP flow from its queuing behavior. We transfer our model into a real-time network emulator and show that it is able to estimate the RTT with an error of only a few milliseconds.Publicationtype: Conference Paper36 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Bandwidth prediction for volatile networks with informer(2023-12-01); 5G networks provide high throughput and low latency connections, crucial for remote monitoring and control of mission-critical operations. Managing buffer levels and accurate bandwidth estimations are essential for low-latency applications. However, wireless networks are susceptible to fluctuations in quality metrics due to mobility and interference, impacting link utilization. Sudden quality deterioration can lead to lower Quality-of-Experience (QoE). To address this, we propose a neural network-based bandwidth prediction system. Our system utilizes historical data for time-series forecasting using the Informer model. It achieves 10% lower errors on a publicly available LTE dataset and 51% lower errors on a publicly available 5G dataset. Future work includes multivariate predictions and the creation of a new 5G dataset.Publicationtype: Conference Paper27 12