Student Work

Next generation mobile networks are envisioned to cope with heterogeneous applications with diverse requirements. To this end, 5G is paving the way towards more scalable and higher performing deployments. This leads to a revised architecture, where the majority of the functionalities are implemented as network functions, which could be scaled up/down depending on the application requirements. 

3GPP has already released the 5G architecture overview, however there exists no actual open source deployment of RAN functionalities. This will be crucial towards the evaluation of the Core network both in terms of scalability and performance. In this thesis, the student shall understand the 5G standardization, especially the control plane communication between the RAN and 5G Core. Further, an initial RAN function compatible with the 5G standards shall be implemented and evaluation of control plane performance will be carried out. 

• Strong knowledge on programming languages Python, C++ or Java.
• Knowledge about mobile networking is necessary.
• Knowlegde about 4G/5G architecture is a plus.

We are looking for a working student to help teaching assistants with Tactile Internet Lab. Prerequisites are as follows:

• Good knowledge in Python or C++ programming languages
• Basic knowledge in Linux
• Fundamentals of computer networking, in particular socket programming

Network slicing is a novel approach used in 5G networks to enable the deployment and coexistence of heterogeneous network with various Quality of Service (QoS) requirements in the same physical infrastructure. In the Radio Access Network (RAN) the network slicing concept is complex is due to the stochastic nature of wireless channels and scarce resources. Vast of ongoing research deal with optimization approaches for RAN slicing, however most of the focus is on the downlink scenario. Nonethess, a joint optimization of downlink and uplink scenarios can render the problem more complex, but on the other hand can procude better results for the overal system behavior.

In this master's thesis the student will focus on a combined downlink/uplink scenario of a cellular system and provide a joint optimization algorithm to enhance the network performance. 

• Basic knowledge of cellular systems 4G/5G.
• Good knowledge of programming languages Python, Matlab.
• Good mathematical background, especially on optimization techniques.
• Knowlegde of tools such as Gurobi is a plus.

Network slicing is a new emerging technique introduced in 5G to boost network performance and accomodate the new heterogeneous requirements of upcoming applications. To this end this has attracted a lot of attention in the state-of-the-art where there is vast of ongoing research in resource allocation and network efficiency in the RAN domain.

The focus of this thesis will be on development and implementation of heuristic approaches for increasing efficiency in resource allocation and network performance. 

• Strong mathematical background.
• Solid programming skills (python, matlab, c++).
• Knowledge of optimization techniques is a plus.

Software-Defined Networking (SDN) is proposed as at technic to increase the network performance by decoupling the control from the data plane of commodity hardware. Recently, SDN has been proposed as a solution to further improve the Radio Access Network (RAN) side of the network. To this aim the notion of SD-RAN controllers has emerged and there is a vast of ongoing research on the performance, evaluation and use of such entities.

In this thesis, the student will have a hands-on experience with FlexRAN controller which is one of the main state-of-the-art SD-RAN controllers. The goal is to enable control of FlexRAN over multiple cells (i.e., eNB/gNB) and ensure a logical flow among the messages exchanged among them. The final evaluation will require a demonstration of the Proof-of-Concept and a set of measurements regarding the cell and SD-RAN controller performance.

• Programming skills in C/C++ is a must, Python knowledge is a plus.
• Knowlegde about SDN, RAN, network slicing is a plus.

5G Networks are anticipated to support the tremendous growth in the traffic demands and the heterogeneity of future applications. In that regard network slicing paves the way towards programmable and flexible networks. On the other hand, delay critical applications require an additional boost on the performance which solutions like Mobile Edge Computing (MEC) or network caching can provide. 

In this thesis the student shall focus on the algorithmic part of the joint network slicing and edge caching. A solution to efficiently manage the resources in order to provide the required performance is needed. To this aim, learning approaches could potentially be utilized for the resource allocation in order to further improve the performance.

• Good knowledge of simulation environments such as Matlab, Python.
• Good mathematical background. Basic knowledge of network slicing and optimization algorithms is a plus.

Internet-based services are demanded by onboard passengers on airplanes. These services must communicate to the ground to access the service endpoints. However, selection of the service endpoints, along with QoS-guaranteed routing can be a challenging task.

In this work, we plan to develop and implement an algorithm based on Simulated Annealing or Tabu Search metaheuristic to solve a multi-period service asseignment and routing problem for Internet-based services in airplanes. For more details, please send an email.

Experience in Python or Java, Optimization, Algorithms

amir.varasteh@tum.de

The lecture Broadband Communication Networks (Prof. Wolfgang Kellerer) teaches network-related methods of mobile communication: WIFI, 2G to 5G cellular networks, etc. In order to bridge the gap between the methods and real life, innovative teaching concepts shall be developed in form of short podcasts where the students learn in short episodes about wireless communication and networking in day to day scenarios. In the podcasts the student should also be introduced to short exercises they can perform on their own.

In order to support designing these podcasts Pro. Kellerer is looking for a student experienced in programming and maybe in podcasts to help him.

Very good programming skills; experience with podcasts; experience with app programming (on android/ios)

Access algortihms are a critical part of 5G networks. Currently, algorithm without direct feedback is used as access algorithms and these show unstable behavior. The main access algorithm with feedback, that is "Tree algorithms" are a prominent candidate to support reliable machine type communication in 5G. 

Another hot topic is the multi packet reception with orthogonalization techniques in code, power or frequency that is then decoded with successive interference cancellation techniques. This is simplified as K multipacket reception to investigate the capability for access algorithms.

In this thesis we plan to analytically investigate the behavior tree algorithms with K packet reception. The thesis will require:

• Good stochastic analysis knowledge
• Good coding in any language for simulation purposes
• Good understanding of the wireless communication
• Motivation to investigate mathematical analysis of system models.

The thesis will be co-supervised by Assoc. Prof. Cedomir Stefanovic from Aalborg University.

We offer a working student position to manage the LKN 5G testbed. The student will document and mantain the existing code, and assist in the development of extensions and new features.

The current 5G testbed consists of two next-generation base stations, three mobile equipments, a centralized unit, and a mobile core network. Work is in progress to virtualize and isolate the different software functions, as recommended in 5G and beyond.

The student will have the opportunity to work with a fully-functional 5G mobile network and help in the testing and developing of new features.

C/C++, 4G mobile networks (LTE), version control (Git), virtualization technologies. Optionally: Python.

Alberto Martínez Alba: alberto.martinez-alba@tum.de

Patrick Kalmbach: patrick.kalmbach@tum.de

5G networks are anticipated to support the tremendous growth in the traffic demands and the heterogeneity of future applications. In that regard, novel techniques such as Software-Defined Networking (SDN), Network Function Virtualization (NFV) pave the way towards programmable and flexible networks. The introduction of SDN/NFV advocates the notion of Network Slicing and Multi-access Edge Computing (MEC). On the one hand, network slicing is a promising approach for 5G to facilitate the deployment of multiple heterogeneous networks on the same physical infrastructure. On the other hand, MEC can be utilized to reduce the potential service delays. In this thesis the student shall focus on the algorithmic part of network slicing and on the performance advantages possibly brought in by the introduction of MEC. To this aim, machine learning approaches are expected be utilized for the cache replacement in order to boost the network performance.<

 This master’s thesis is a collaboration with German Aerospace Center (DLR). In this master thesis the student will  survey the most recent network architectures integrating satellite and terrestrial 5G elements in order to understand the role played by Network Slicing for end-to-end network resource allocation and assess the performance of an exemplary MEC solution in the proposed scenario. Moreover the focus will be on the investigation of the impact of time-varying popularity on caching strategies. 

•  Good knowledge of a simulation environment Matlab, Python.
•  Good mathematical background. Basic knowledge of satellite and cellular communications.

Optical core networks deploy fixed grid in order to accommodate their demands. The trend is however, migrate towards flexgrid networks able to use as much spectrum as required by the demand allowing a better use of the spectrum. However, the Routing and Wavelength Assignment (RWA) paradigm becomes more complex as it has to find the suitable spectrum of the demand.

This thesis will consider two different alternatives to solve the Routing and Spectrum Assignment (RSA) problem. Given a database providing for each (source, destination) pair a set of (route, modulation format, baud rate, OSNR, ….), choose the best route and spectrum for a set of demands.

The implementation will be done in Java. The first alternative is based on an existing work (JOCN2018 paper of Soumplis et al.) and the second alternative will be proposed during the thesis.

The evaluation aims at comparing both solutions in terms of computation time, network utilization, network balancing, blocking probability, energy, etc. Different scenarios will be studied: i) Static, ii) Dynamic sequential: ordered set of demands with Tstart, iii) Dynamic random: set of random demands with (Tstart, Tend)

Java programming skills

Basic knowledge of flexible optical networks

Communication networks form the backbone of our digital society and have become a critical infrastructure. However, the operation of networks today is still a manual and error-prone process, which is worrysome.

We have recently started exploring the vision of self-repairing networks and developed a first approach and software which allows for a fast what-if analysis of MPLS networks [1]: our approach relies on a classic result in formal methods and automatically tests whether network configurations are policy compliant (e.g., "can host A reach host B even under up two 2 link failures?").

While our first results are promising and the approach fast in theory, it is still relatively slow in practice. 

Accordingly, in this project, we would like to explore whether machine learning approaches such as Graph Neural Networks (GNNs) could be used to speed up the network verification. If this is the case, interesting opportunities are opened: for example, it may not only be possible to quickly test whether networks are policy-compliant, but even to automatically propose "fixes" in case they are not.

This is a joint work with University of Vienna, Faculty of Computer Science. A short research visit abroad in Austria might be included.

Required skills: programming and algorithms; interest in networking and machine learning, interest in formal methods a plus

Remark: The software of P-Rex is available and well-documented and could be used as a blackbox during this thesis.

...

...

The student's task is the implementation of a community detection algorithm that is capable of unveiling mixed community membership of hosts. Due to the nature of IP communication the existence of mixed memberships, especially for clients, is highly likely.

Based on this algorithm different traffic traces should be analyzed and the result interpreted. That is, which properties do the identified communities express? Do nodes generally belong to a single community or multiple communities?

As part of this thesis the student has to adapt an existing data preparation pipeline to his needs. This pipeline should transform traffic traces into annotated graphs that can then be analyzed using the implemented algorithm.

• Python
• Networking knowledge
• C++/Numpy
• Data Mining
• Statistics

...

Designing IP-address schemes is a crucial task in networking. Forwarding of data packets is performend based on IP addresses based on lookup tables. However, table space is limited. IP addresses are thus required to efficiently encode node location in the graph to reduce the number of table entries. Recent trends in networking to include machine learning in the match action pipeline of switches further increase the need for predictable addresses.

The goal of this thesis is to investigate whether IP address prefixes can be learned for topologies based on bernoulli embeddings of graph nodes. The performance of the code is evaluated based on classification performance. Further, the student should investigate the required size of codes to enable reliable forwarding.

- Machine Learning

- Python

- Tensoflow

- Networking

The goal of this thesis is the classification of applications in IP-to-IP communication. The student should extract traffic dispersion graphs from traffic traces and use graph attention neural networks to distinguish between TDGs of different applications.

• Python
• Tensorflow
• Machine Learning

In this work, we would like to implement a nested approach to make three decisions in a Space-Air-Ground Integrated Network: 1) Where to place Internet-based services for airplane passengers? 2) How to route the traffic from the plane to the VM? 3) Are VM migrations necessary over time? 

Experience in Python or Java, Mathematical Optimization, Algorithms

amir.varasteh@tum.de

Resource Management (VM Location, Routing, and Migration) in while airplanes are flying. An iterative approach tackles the problem by solving the small-sized problems iteratively. In this work, we would like to implement and evaluate this approach in a Space-Air-Ground Integrated scenario, where we provide QoS-guranteed Internet-based services to passengers while airplanes are flying.

Experience in Python or Java, Mathematical Optimization, Algorithms

amir.varasteh@tum.de

Sensor to Cloud Solution via a Gateway

Das Thema dieser Bachelorthesis ist die Entwicklung, Optimierung und Evaluation des proprietären Brandmeldebussystems LSNi1 der Firma Bosch Sicherheitssysteme GmbH in Grasbrunn.

Brandmeldeanlagen sind ein bestehender notwendiger Teil der Gebaudetechnik und sollen fur neue vernetzte IoT-Dienste verwendet werden. Aufgrund immer höheren Anforderungen dieser Dienste soll die Datenrate uber den Brandmeldebus gesteigert werden. Zur Zeit wird das Bussystem zur verhaltnismäßig datenarmen Alarmabfrage und Antwort der Netzelemente verwendet. Ein wichtiger Punkt ist dabei, die Systemcharakteristika des Brandmeldesystems nicht zu verschlechtern. Solche Netzwerke sind als Sicherheitssysteme deklariert und mussen daher äußerst zuverlässig in Sachen Ausfallsicherheit und Fehlererkennung sein.

Die Aufgabe besteht darin, eine neue Übertragungstechnik mit höherer Datenrate auf der physikalischen Schicht des Busses zu finden und diese mit Hilfe eines Prototypen umzusetzen. Die Optimierung des Prototypen soll durch Berechnung und Experimentieren mit Systemelementen ausgearbeitet werden. Daraufhin werden verschiedene Testaufbauten, im firmeneigenen Labor getestet. Die dabei aufgenommenen Daten werden über ein entwickeltes Matlab-Evaluierungsprogramm ausgewertet, um eindeutige Aussagen über die Funktionalitat des Systems zu geben. Eine besondere Herausforderung bei Systemen dieser Art sind die hohen Kabellängen und die große Anzahl an Systemelementen auf dem Bus. Mit den ausgewerteten Ergebnissen soll überpruft werden, in welchem Umfang die Datenrate auf dem Bus gesteigert werden kann.

N.A.

LiFi is becoming an increasingly important technology as the unlicensed ISM band gets overcrowded. LiFi, with its high data rates, emerges as a promising solution to provide connectivity in an aircraft using overhead LED lights thereby reducing the interference with other wireless technologies and reducing the overall aircraft radio emissions. The integration of LiFi into existing communication systems is best envisioned in the form of wireless Heterogeneous Networks or HetNets where the short-range, additional capacity providing LiFi cells complement the broader coverage providing WiFi cells. Any user device in such a HetNet is equipped with multiple wireless interfaces i.e. LiFi and WiFi.

In this work, the student is expected to design and evaluate a reliable wireless access technology selection algorithm that performs load balancing between LiFi and WiFi.

High reliablity and low latency requiring applications, namely Industrial IoT, (IIoT) cannot be supported by the current version of the mobile networks standard that is the 5G. 5G also known as New Radio, is currently on going through the standardization process and one of the critical topics is to support IIoT applications. 

There are many solutions proposed for radio resource management to incorporate IIoT in 5G. Modern Random Access techniques are the most prominent solution for efficient radio resource management through use of interference cancellation. 

In this work the main Modern Random Access algorithms are optimized for low number of users and high reliability and low latency constraints. 

A Service Function Chain (SFC) can be deployed by utilizing Network Function Virtualization (NFV) concept. A challenge during the lifetime of SFCs can over- / underload a Virtual Network Function (VNF). To solve this issue, firsly, the under- / overload bottleneck should be identified. Secondly, an algorithm must be solved to solve the under- / overloaded situation efficiently.

In this work, we plan to design and evaluate an optimized strategy to identify and cope with under / over deployed SFCs. We want focus on a distributed optimization approach, called Alternating Direction Method of Multipliers (ADMM).

Mathematical Optimization, Algorithms, Java / Python

amir.varasteh@tum.de

Introduction to Software Defined Networking (SDN) and Network Virtualization paradigms has brought new challenges to tackle. In this environment, network switches communicate to SDN controllers through a hypervisor. Therefore, considering a network graph, three questions may come up: 1) Where to deploy SDN controllers? 2) Where to deploy SDN hypervirors? 3) How to connect network switches to the respective SDN controllers to meet the traffic dynamicity and QoS requirements?

In this work, we plan to design and evaluate an optimization framework to optimally answer the above questions.

Mathematical Optimization, Algorithms, Java / Python

amir.varasteh@tum.de

Softwarized wireless sensor networks base station to prototype 5G-like ecosystem using cheap sensor to test out most recent radio resource management techniques.  

yle="margin: 0px 0px 1em; color: #333333; font-family: Arial, sans-serif; font-size: 14px;">Network slicing is a novel approach used in 5G networks to enable the deployment and coexistence of heterogeneous networks with different Quality of Service requirements in the same physical infrastructure. In the Radio Access Network (RAN) the network slicing problem is complex due to the stochastic nature of wireless channels and scarce resources. To this end efficient algorithms are required. This has attracted a lot of attention in the literature where there are works dealing with RAN slicing and QoS provisioning but focusing on a single cell scenario. However, for specific applications (i.e., aircraft in-cabin communication, reliability critical tasks) one cell might not be sufficient. Therefore, the need of multiple-cells becomes mandatory.

yle="margin: 0px 0px 1em; color: #333333; font-family: Arial, sans-serif; font-size: 14px;">In this master thesis the student will focus on the downlink scenario of a cellular system consisting of multiple-cells. The focus will be on the dynamic allocation of resources with regard to slicing requests for guaranteeing QoS and isolation among them. Moreover, an optimization problem has to be developed analytically and further evaluated with extensive simulations to prove the efficiency of the approach. Finally, for specific metrics such as reliability this method shall be compared with existing state-of-the-art approaches.

yle="list-style-type: square; margin-left: 0px; padding-left: 20px; color: #333333; font-family: Arial, sans-serif; font-size: 14px;">
• yle="padding-left: 0.3em;">Good knowledge of a simulation environment Matlab, Python
• yle="padding-left: 0.3em;">Good mathematical background. Knowledge of optimization techniques and tools such as Gurobi is a plus.

TBD

Current mobile devices support several wireless technologies to communicate with the outer world. To this end, these devices often include multiple LTE, WiFi, or BlueTooth interfaces. In addition, base stations also have several wired or wireless interfaces to communicate with one another or with the core network. This adds a new degree of freedom to the problem of optimally selecting data flows within a mobile network, which is motivated by the ever-changing nature of wireless channels. In this thesis, a flexible mobile network supporting live selection of interfaces will be analyzed. Available algorithms to adaptively select interfaces and reconfigure data flows will be explored. A flexibility framework will be used in order to highlight the importance of request changes and reaction time.

Familiarity with mobile and wireless networks. Experience with MATLAB, Python or other programming languages or simulation environments. 

Testbed with QT GUI and 4 mini USRPs for communication. GNURadio implementation for the SDRs.

The goal of this thesis is the implementation and evaluation of a deep reinforcement learning based approach to traffic engineering in datacenters. Your task is the implementation of a packet-level simulator in NS3 and the integration of our in-house deep-rl framework in this simulator. Further, you should evaluate different neural architectures as well as data-center topologies and compare the performance obtained with deep RL to Equal Cost Multi-Pathing (ECMP).

In this internship, the student has to evaluate the impact of reconfiguring the network on the performance of transport protocols.

Thanks to the ease of deployment and low cost, Wireless Sensor Networks (WSN) is a good candidate technology for many applications. In the context of industrial applications, WSN provides the necessary communication infrastructure for sensors and actuators to wirelessly operate in closed-loop control systems called Networked Control Systems (NCSs).

In state-of-the-art NCSs, a remote state estimator calculates the Minimum Mean Square Error (MMSE) estimate of the system’s state, which is then used by the controller to compute the actuation command. WSN devices, however, are subject to packet loss due to the low-power communication technology and external disturbances. This effect severely degrades the quality of estimation and can lead to the instability of the system under control. For this reason, an MMSE estimator operating over lossy WSN must take the stochastic packet loss into account [1,2].

In this work:

• An industrial wireless sensor network will be deployed using Zolertia Re-Motes and the Contiki-NG firmware.
• A measurement-based model of the WSN channel quality will be derived and included in the MMSE filter model.
• The quality of estimation of the MMSE filter will be evaluated and compared to [1].

This work will consist of the significant amount of programming for embedded devices, and for a large part also of processing the measurements data.

[1] Soleymani, Touraj, et al. "Covariance-based transmission power control for estimation over wireless sensor networks." 2018 European Control Conference (ECC). IEEE, 2018.

[2] Zoppi, Samuele, et al. "Transmission Power Control for Remote State Estimation in Industrial Wireless Sensor Networks." arXiv preprint arXiv:1907.07018 (2019).

• Strong C and Python programming skills.
• Good knowledge of wireless systems and protocols (WSN).
• Basic knowledge of LTI control systems. 
• Experience with python data processing tool is beneficial.
• Experience with embedded systems is beneficial but not required.

In this work, we plan to implement several Virtual Network Functions (VNFs) for NAT, Firewall, IDS, etc. on Virtual Machines and Contrainers. We plan to characterize the VNFs in terms of resource usage. Thereafter, we study the reconfigurability and its overhead on the performance of the VNFs. We would like to measure the metrics such as throughput, latency, etc.

programming, linux

amir.varasteh@tum.de

P4 is a novel programming language for programming networking devices (switches and NICs). It allows you to describe how the networking devices will process the packets in a high-level language. This programmability paved the way to many different applications and innovations that were not possible before, which made it a hot research topic nowadays. The objective of this Master Thesis/internship topic is to evaluate the performance of such devices. The main scope of this thesis/ internship work is to measure and model the performance of P4-programmable devices. Note that there are multiple related subtopics, so the required tasks are flexible and will be based on student's interest and skills. The main requirements are being motivated and having basic programming and networking skills. Knowledge about SDN and P4 is a plus. 

Motivation, Basic Programming and Networking skills

P4 is a novel programming language for programming networking devices. It enables the network engineer to describe the behavior in a simple language. Switches via P4 still needs to be communicated with a controller as in any SDN architecture, however, currently available. The latter is the reason for designing a new southbound interface, "P4 Runtime". The objective of this project is to evaluate the performance of the P4Runtime protocol and extend the existing SDN controller's benchmarking tools. A detailed analysis of the results will be performed. The student wants to work on this project in collaboration with Nokia Bell Labs and get a great experience on the trends in networking and SDN. In addition, 

Motivation and good analysis skills, Programming skills: JAVA C ++, SDN and programmable data plan knowledge is a plus

You are interested in the internal workings of a data-center? You want to get a head-start in programmable data-planes? You want to work on an actual problem? Then this is your chance!

Load balancing and traffic engineering within data-centers is still an open problem (belief it or not). Programmable data-planes offer new possibilities in tackling those problems. However, the topic is new and not well understood yet. Check out the publication "HULA: Scalable load balancing using programmable data planes" to get an idea of what is awaiting you.

Your job in this project is the re-implementation and evaluation of an in-data-plane load-balancing algorithm. You will obtain a deep understanding of the fundamental problems in data-center networking and novel technologies such as P4 and SDN.

You also want to do a Forschungspraxis or Master Thesis? No problem! This project allows you to continue by bringing machine learning into play. Our goal is a network that learns traffic engineering by itself without human intervention. Just let us now.

• C++
• Discrete Event Simulation
• Python

Today, Internet-based services are delivered to on-board passengers on airplanes. Improving the service availablity can be an issue for airline companies and their passengers. 

In this work, we plan to design a reliable approach based on Generalized Assignment Problem, considering the flying airplanes. We want to implement the proposed model and evolve the performance of it in a simulation environment.

Algorithms, Python

amir.varasteh@tum.de

...

...

In this work, the student will survey different P4 software switches and evaluate its performance.

Survey of software switches. Setup of physical and virtual machine-based measurement system. Code analysis of Open vSwitch user space. Reevaluation of existing Open vSwitch measurements. Study of Bayesian optimization concept.

Python, C++, Linux

Network Function Virtualization (NFV) is becoming a promissing technology in modern networks. A challenging problem is determining the placement of Virtual Network Functions (VNFs). In this work, we plan to implement existing algorithms for embedding VNFs chains in NFV-enabled networks. 

Experience in Python or Java, object oriented programming

amir.varasteh@tum.de

The Wireless Sensor Networks lab offers the opportunity to develop software solutions for the wireless sensor networking system, targeting innovative applications. For the next semester, a position is available to assist the participants in learning the programming environment and during the project development phase. The lab is every Tuesday from 15:00 to 18:00.

Solid knowledge in Wireless Communication: PHY, MAC, and network layers. Solid programming skills: C/C++. Linux knowledge. Experience with embedded systems and microcontroller programming knowledge is preferable.

The wireless sensor networks lab offers the opportunity to develop software solutions for wireless sensor networking systems, targeting innovative applications. For the next semester, a position is available to assist the participants in learning the programming environment and during the project development phase. The lab is every Tuesday from 15:00 till 18:00.

The yle="color: #333333; font-family: Arial, sans-serif; font-size: 14px;">Software-Defined Networking (SDN) lab offers the opportunity to work with real hardware on interesting and entertaining projects related to the SDN network paradigm. For the next semester, a position is available to assist the teaching assistants for the lab (definition and preparation of the assignments, preparation of the hardware, etc.).

yle="list-style-type: square; margin-left: 0px; padding-left: 20px; color: #333333; font-family: Arial, sans-serif; font-size: 14px;">
• yle="padding-left: 0.3em;">Solid knowledge in computer networking (TCP/IP, SDN)
• yle="padding-left: 0.3em;">Solid knowledge of networking tools and Linux (iperf, ssh, etc)
• yle="padding-left: 0.3em;">Good programming skills: C/C++, Python

This working student position supports us in conducting measurement and implementing network algorithms and solutions for various use cases.

Machine Learning (ML) and Artificial Intelligence (AI) are also a current hype in networking research. Within, the applications of ML and AI range from data center network optimization to anomaly detection in campus and enterprise networks. As we are currently conducting a lot of research in this area of application of ML/AI, we are always looking for students willing and able to support us. So, if you are interested in ML/AI and its application to networking, please contact us.

We offer you:

• Possibility to extend your skills in ML/AI, programming and networking

• Possibility to become (Co)-author of publications already before graduating

• Access to compute cluster and data center-like networking environments

We need:

• A student with good programming skills in Python and C++

• Basic knowledge in data science

• Basic understanding of networking: TCP/IP, UDP, BGP, RIP, FatTree Topologies, ...

• Basic knowledge in algorithms and optimization: search, sort, mathematical problem formulation, …

• Basic skills in Linux and server administration

Python, C++, Data Science, Basic Networking