Skip to content

Final publication in our project: “Machine Learning at the Mobile Edge: The Case of Dynamic Adaptive Streaming over HTTP (DASH)”

Our TNSM 2022 journal article is the final publication funded by this project. The full title is “Machine Learning at the Mobile Edge: The Case of Dynamic Adaptive Streaming over HTTP (DASH)”. This is joint work done in collaboration with FBK between Rasoul Behravesh (FBK), Akhila Rao (RISE), Daniel F Perez-Ramirez (RISE), Davit Harutyunyan (Corporate Research, Robert Bosch GmbH, work done at FBK), Roberto Riggio (Universita Politecnica delle Marche, work done at FBK), and Magnus Boman (KTH).


Here is the abstract and a link to the paper. The code and dataset links are in the Releases page.


“Dynamic Adaptive Streaming over HTTP (DASH) is a standard for delivering video in segments and adapting each segment’s bitrate (quality), to adjust to changing and limited network bandwidth. We study segment prefetching, informed by machine learning predictions of bitrates of client segment requests, implemented at the network edge. We formulate this client segment request prediction problem as a supervised learning problem of predicting the bitrate of a client’s next segment request, in order to prefetch it at the mobile edge, with the objective of jointly improving the video streaming experience for the users and network bandwidth utilization for the service provider. The results of extensive evaluations showed a segment request prediction accuracy of close to 90% and reduced video segment access delay with a cache hit ratio of 58%, and reduced transport network load by lowering the backhaul link utilization by 60.91%.”


Link to the paper:

Alexandros’ licentiate defense

Congratulations on Alexandros for defending his licentiate thesis titled “Understanding the Capabilities of Route Collectors to Observe Stealthy Hijacks”! The supervisors are Marco Chiesa and Dejan Kostic. Thanks to the advanced reviewer Prof. Gerald Q. Maguire Jr., the special reviewer Prof. Alberto Dainotti, and the examiner Prof. Roberto Guanciale for their thorough work.

You can find more about Alexandros’ work by reading this thesis here.

From left to right: Roberto Guanciale, Alexandros Milolidakis, and Marco Chiesa.

Our PAM 2021 paper: “What you need to know about (Smart) Network Interface Cards”

In our PAM 2021 paper, we study the performance of (smart) Network Interface Cards (NICs) for widely deployed packet classification operations, focusing on four 100-200 GbE NICs from one of the largest NIC vendors worldwide.

We show that the forwarding throughput of the tested NICs sharply degrades when i) the forwarding plane is updated and ii) packets match multiple forwarding tables in the NIC.

Moreover, we uncover that the standard DPDK rule update API realizes slow & non-atomic rule updates using a sequence of rule insertion and deletion operations.

We solve this problem by introducing a direct in-memory rule update mechanism that achieves 80% higher throughput than the standard DPDK rule update API.

This is joint work with Georgios P. Katsikas, Tom Barbette, Marco Chiesa, Dejan Kostic, and Gerald Q. Maguire Jr.

Our ASPLOS ’21 Paper: “PacketMill: Toward Per-Core 100-Gbps Networking”

ASPLOS ’21 will feature Alireza’s presentation of our paper titled “PacketMill: Toward Per-Core 100-Gbps Networking”. This is joint work with Alireza Farshin, Tom Barbette, Amir Roozbeh, Gerald Q. Maguire Jr., and Dejan Kostić.

The full abstract (with the video and more resources below):

We present PacketMill , a system for optimizing software packet processing, which (i) introduces a new model to effjciently manage packet metadata and (ii) employs code-optimization techniques to better utilize commodity hardware. PacketMill grinds the whole packet processing stack, from the high-level network function confjguration fjle to the low-level userspace network (specifjcally DPDK) drivers, to mitigate ineffjciencies and produce a customized binary for a given network function. Our evaluation results show that PacketMill increases throughput (up to 36.4Gbps – 70%) & reduces latency (up to 101µs – 28%) and enables nontrivial packet processing (e.g., router) at ≈100Gbps , when new packets arrive > 10 × faster than main memory access times, while using only one processing core

PacketMill Webpage:

PacketMill Paper:
PacketMill source code:
PacketMill Slides with English transcripts:


Timely survey on applying machine learning to solve complex combinatorial optimization problems over networks

Effective use of networked resources requires the ability to solve complex large-scale optimization problems fast while accounting for many input variables and performance requirements, such as end-to-end latency. Advancing beyond heuristic approaches, we begin with surveying the current state of applied machine learning to solve complex combinatorial optimization problems over networks. In our IEEE Access article titled “Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking”, we qualitatively analyse existing learning approaches and applications in the networking domain. Full abstract is as follows:


“Existing approaches to solving combinatorial optimization problems on graphs suffer from the need to engineer each problem algorithmically, with practical problems recurring in many instances. The practical side of theoretical computer science, such as computational complexity, then needs to be addressed. Relevant developments in machine learning research on graphs are surveyed for this purpose. We organize and compare the structures involved with learning to solve combinatorial optimization problems, with a special eye on the telecommunications domain and its continuous development of live and research networks.”


This work was done by Natalia Vesselinova (RISE), Rebecca Steinert (RISE), Daniel Felipe Perez-Ramirez (RISE) and Magnus Boman (KTH).