Patrick Kalmbach

Patrick Kalmbach

Auto-generated profile, based on publicly available information

Patrick Kalmbach

Chair of Communication Networks, Technical University of Munich, Munich, Germany

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 May 2023 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
APAnna Prado
Anna Prado
FSFranziska Stöckeler
Franziska Stöckeler
FMFidan Mehmeti
Fidan Mehmeti
PKPatrick Krämer
Patrick Krämer
WKWolfgang Kellerer
Wolfgang Kellerer
Mobility management in 5G is challenging, and at higher frequencies, a larger number of cells is needed to provide similar coverage to that in 4G. Consequently, Base Stations (BSs) are placed much more densely and users experience frequent handovers, reducing network capacity. Advanced handover techniques are needed in 5G to perform smooth network operation. In this paper, we formulate an optimization problem, whose goal is to strive for fairness in data rates among users and to reduce handovers. To accomplish that, we consider jointly the decisions when to handover and to which BS a user is to be assigned. This is an integer nonlinear program, and by relaxing it, we obtain an upper bound. Further, due to its NP-hardness, we propose a centralized and a multi-agent Deep Q Network (DQN)-based algorithm, which both find near-optimal user-to-BS assignments. We evaluate our Reinforcement Learning-based solutions for networks of different sizes and users with different velocities. We compare our approaches with baselines and show that they outperform them considerably in terms of fairness and radio link failures while being within 95% of the optimum. Our DQN algorithms also reduce the handover rate by up to 93% and avoid ping-pong handovers almost completely.

1 October 2016
Verified
Conference Paper
Closed access
ABAndreas Blenk
Andreas Blenk
PKPatrick Kalmbach
Patrick Kalmbach
PSPatrick van der Smagt
Patrick van der Smagt
WKWolfgang Kellerer
Wolfgang Kellerer
The allocation of physical resources to virtual networks, i.e., the virtual network embedding (VNE), is still an on-going research field due to its problem complexity. While many solutions for the online VNE problem exist, only few have focused on methods that can be generally applied for optimization of online embeddings. In this paper, we propose an admission control based on a Recurrent Neural Network (RNN) to improve the overall system performance for the online VNE problem. Before running a VNE algorithm to embed a virtual network request, the RNN predicts whether the request will be accepted by the VNE algorithm based on the current state of the substrate and the virtual network request (VNR). The RNN prevents VNE algorithms from spending time on VNRs that are either infeasible or that cannot be embedded in acceptable time. In order to train and operate the RNN efficiently, we additionally propose new representations for substrate networks and virtual network requests. The representations are based on topological and network resource features to represent the substrate network and the VNRs with low computational complexity. Via simulations, we show that our admission control reduces the overall computational time for the online VNE problem by up to 91 % while preserving VNE performance on average. Using our new substrate and request representations, the RNN achieves an accuracy ranging between 89 % and 98 % for different VNE algorithms, substrate sizes, and VNR arrival rates.

7 August 2017
Verified
Conference Paper
Open access
PDF file
ABAndreas Blenk
Andreas Blenk
PKPatrick Kalmbach
Patrick Kalmbach
WKWolfgang Kellerer
Wolfgang Kellerer
SSStefan Schmid
Stefan Schmid
At the heart of many computer network planning, deployment, and operational tasks lie hard algorithmic problems. Accordingly, over the last decades, we have witnessed a continuous pursuit for ever more accurate and faster algorithms. We propose an approach to design network algorithms which is radically different from most existing algorithms. Our approach is motivated by the observation that most existing algorithms to solve a given hard computer networking problem overlook a simple yet very powerful optimization opportunity in practice: many network algorithms are executed repeatedly (e.g., for each virtual network request or in reaction to user mobility), and hence with each execution, generate interesting data: (problem,solution)-pairs. We make the case for leveraging the potentially big data of an algorithm's past executions to improve and speed up future, similar solutions, by reducing the algorithm's search space. We study the applicability of machine learning to network algorithm design, identify challenges and discuss limitations. We empirically demonstrate the potential of machine learning network algorithms in two case studies, namely the embedding of virtual networks (a packing optimization problem) and k-center facility location (a covering optimization problem), using a prototype implementation.

1 January 2019
Verified
Conference Paper
Open access
JZJohannes Zerwas
Johannes Zerwas
PKPatrick Kalmbach
Patrick Kalmbach
LHLaurenz Henkel
Laurenz Henkel
GRGábor Rétvári
Gábor Rétvári
WKWolfgang Kellerer
Wolfgang Kellerer
SSStefan Schmid
Stefan Schmid
Communication networks have not only become a critical infrastructure of our digital society, but are also increasingly complex and hence error-prone. This has recently motivated the study of more automated and "self-driving" networks: networks which measure, analyze, and control themselves in an adaptive manner, reacting to changes in the environment. In particular, such networks hence require a mechanism to recognize potential performance issues. This paper presents NetBOA, an adaptive and "data-driven" approach to measure network performance, allowing the network to identify bottlenecks and to perform automated what-if analysis, exploring improved network configurations. As a case study, we demonstrate how the NetBOA approach can be used to bench-mark a popular software switch, Open vSwitch. We report on our implementation and evaluation, and show that NetBOA can find performance issues efficiently, compared to a non-data-driven approach. Our results hence indicate that NetBOA may also be useful to identify algorithmic complexity attacks.

25 May 2022 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
PKPatrick Kramer
Patrick Kramer
PDPhilip Diederich
Philip Diederich
CKCorinna Kramer
Corinna Kramer
RPRastin Pries
Rastin Pries
WKWolfgang Kellerer
Wolfgang Kellerer
ABAndreas Blenk
Andreas Blenk
Realizing Service Function Chaining with a micro-service-based architecture results in an increased number of computationally cheap Virtual Network Functions (VNFs). Pinning cheap VNFs to dedicated CPU cores can waste resources since not every VNF fully utilizes its core. Thus, cheap VNFs should share CPU cores to improve resource utilization. However, sharing cores can result in degraded performance due to interference between VNFs, even in mildly loaded scenarios. We propose D2A , a system that combines Neural Combinatorial Optimization, Machine Learning (ML)-based Digital Twins (DTs), and Game Theory to optimize VNF assignments. Measurements in a testbed show that D2A increases throughput by up to 46% and reduces latency by up to 93%, compared to three baseline algorithms. Using an ML-based DT to model VNF interference increases throughput by up to 11%, and reduces latency by up to 90% compared to an analytical model of the system.

1 May 2017
Verified
Conference Paper
Closed access
PKPatrick Kalmbach
Patrick Kalmbach
ABAndreas Blenk
Andreas Blenk
MKMarkus Kluegel
Markus Kluegel
WKWolfgang Kellerer
Wolfgang Kellerer