Alexander Dietmüller


Last Name

Dietmüller

First Name

Alexander

ORCID

0000-0003-3769-3958

Organisational unit

Filters

2017 - 201932020 - 202510
Reset filters

Search Results

Publications 1 - 10 of 13
  • A neuromorphic controller for a robotic vehicle equipped with a dynamic vision sensor
    Item type: Conference Paper
    Blum, Hermann; Dietmüller, Alexander; Milde, Moritz; et al. (2017)
    Robotics: Science and Systems XIII
  • Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems
    Item type: Conference Paper
    Milde, Moritz B.; Dietmüller, Alexander; Blum, Hermann; et al. (2017)
    Proceedings of the 2017 IEEE International Symposium on Circuits and Systems
  • Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System
    Item type: Journal Article
    Milde, Moritz B.; Blum, Hermann; Dietmüller, Alexander; et al. (2017)
    Frontiers in Neurorobotics
    Neuromorphic hardware emulates dynamics of biological neural networks in electronic circuits offering an alternative to the von Neumann computing architecture that is low-power, inherently parallel, and event-driven. This hardware allows to implement neural-network based robotic controllers in an energy-efficient way with low latency, but requires solving the problem of device variability, characteristic for analog electronic circuits. In this work, we interfaced a mixed-signal analog-digital neuromorphic processor ROLLS to a neuromorphic dynamic vision sensor (DVS) mounted on a robotic vehicle and developed an autonomous neuromorphic agent that is able to perform neurally inspired obstacle-avoidance and target acquisition. We developed a neural network architecture that can cope with device variability and verified its robustness in different environmental situations, e.g., moving obstacles, moving target, clutter, and poor light conditions. We demonstrate how this network, combined with the properties of the DVS, allows the robot to avoid obstacles using a simple biologically-inspired dynamics. We also show how a Dynamic Neural Field for target acquisition can be implemented in spiking neuromorphic hardware. This work demonstrates an implementation of working obstacle avoidance and target acquisition using mixed signal analog/digital neuromorphic hardware.
  • Adaptive Network Traffic Modeling
    Item type: Doctoral Thesis
    Dietmüller, Alexander (2024)
    The Internet is a decentralized and constantly growing control system that has become an integral part of the lives of over 5.3 billion people. With this scale comes a vast array of applications. Performant and robust control of applications like video streaming requires modeling network traffic, such as estimating whether the network is congested or how long it will take to transmit data. The complexity of this modeling problem has steadily increased over time: the model space is ever-growing with each new network algorithm and application, while observable signals have remained largely unchanged. It has become extremely difficult, and perhaps intractable, to model network traffic from first principles, and research has increasingly turned to machine learning (ML) to learn models from data. This dissertation explores the opportunities and challenges of using ML for network traffic modeling and additionally investigates how advances in programmable networking may provide better signals. First, we study learning over time. We present Memento, a sample selection system for updating ML models with a focus on tail performance while avoiding unnecessary retraining. The key insight behind Memento is that a smart data selection is crucial to maintain representative training data and to decide when retraining models with the selected data is beneficial. Second, we investigate learning over space, the generalization of models to other network environments and tasks, and present a Network Traffic Transformer (NTT). NTT is a pre-trained Transformer-based model that can be efficiently fine-tuned to different networks and prediction tasks. Third, we study the underlying problem of learning latent network state common to many prediction tasks. Through in-depth analysis and comparison of several ML-based models for video streaming, we gain important insights into modeling strategies and model generalizability. Finally, we explore the potential of programmable networks to enhance observable signals by programmatically processing all packets in the network, albeit with limited computational resources. We present FitNets, which makes the most of constrained programmability with hardware-software co-design: FitNets learns accurate distributions of network traffic features in the control plane, enabled by efficient model scoring in the data plane.
  • Data plane: Stop sampling and start scoring!
    Item type: Conference Poster
    Dietmüller, Alexander; Fragkouli, Georgia; Vanbever, Laurent (2023)
  • P2GO: P4 Profile-Guided Optimizations
    Item type: Conference Paper
    Wintermeyer, Patrick; Apostolaki, Maria; Dietmüller, Alexander; et al. (2020)
    Proceedings of the 19th ACM Workshop on Hot Topics in Networks
    Programmable devices allow the operator to specify the data-plane behavior of a network device in a high-level language such as P4. The compiler then maps the P4 program to the hardware after applying a set of optimizations to minimize resource utilization. Yet, the lack of context restricts the compiler to conservatively account for all possible inputs -- including unrealistic or infrequent ones -- leading to sub-optimal use of the resources or even compilation failures. To address this inefficiency, we propose that the compiler leverages insights from actual traffic traces, effectively unlocking a broader spectrum of possible optimizations. We present a system working alongside the compiler that uses traffic-awareness to reduce the allocated resources of a P4 program by: (i) removing dependencies that do not manifest; (ii) adjusting table and register sizes to reduce the pipeline length; and (iii) offloading parts of the program that are rarely used to the controller. Our prototype implementation on the Tofino switch automatically profiles the P4 program, detects opportunities and performs optimizations to improve the pipeline efficiency. Our work showcases the potential benefit of applying profiling techniques used to compile general-purpose languages to compiling P4 programs.
  • A New Hope for Network Model Generalization
    Item type: Other Conference Item
    Dietmüller, Alexander; Ray, Siddhant; Jacob, Romain; et al. (2022)
  • A New Hope for Network Model Generalization
    Item type: Conference Paper
    Dietmüller, Alexander; Ray, Siddhant; Jacob, Romain; et al. (2022)
    HotNets '22: Proceedings of the 21st ACM Workshop on Hot Topics in Networks
    Generalizing machine learning (ML) models for network traffic dynamics tends to be considered a lost cause. Hence for every new task, we design new models and train them on model-specific datasets closely mimicking the deployment environments. Yet, an ML architecture called Transformer has enabled previously unimaginable generalization in other domains. Nowadays, one can download a model pre-trained on massive datasets and only fine-tune it for a specific task and context with comparatively little time and data. These fine-tuned models are now state-of-the-art for many benchmarks. We believe this progress could translate to networking and propose a Network Traffic Transformer (NTT), a transformer adapted to learn network dynamics from packet traces. Our initial results are promising: NTT seems able to generalize to new prediction tasks and environments. This study suggests there is still hope for generalization through future research.
  • SP-PIFO: Approximating Push-In First-Out Behaviors using Strict-Priority Queues
    Item type: Conference Paper
    Gran Alcoz, Albert; Dietmüller, Alexander; Vanbever, Laurent (2020)
    Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation
    Push-In First-Out (PIFO) queues are hardware primitives which enable programmable packet scheduling by allowing to perfectly reorder packets at line rate. While promising, implementing PIFO queues in hardware and at scale is not easy: only hardware designs (not implementations) exist and they can only support about 1000 flows. In this paper, we introduce SP-PIFO, a programmable packet scheduler which closely approximates the behavior of PIFO queues using strict-priority queues—at line rate, at scale, and on existing devices. The key insight behind SP-PIFO is to dynamically adapt the mapping between packet ranks and available queues to minimize the scheduling errors. We present a mathematical formulation of the problem and derive an adaptation technique which closely approximates the optimal queue mapping without any traffic knowledge. We fully implement SP-PIFO in P4 and evaluate it on real workloads. We show that SP-PIFO: (i) closely matches ideal PIFO performance, with as little as 8 priority queues; (ii) arbitrarily scales to large amount of flows and ranks; and (iii) quickly adapts to traffic variations. We also show that SP-PIFO runs at line rate on existing programmable data planes.
  • Poster: Learning distributions to detect anomalies using all the network traffic
    Item type: Other Conference Item
    Dietmüller, Alexander; Fragkouli, Georgia; Vanbever, Laurent (2023)
    ACM SIGCOMM '23: Proceedings of the ACM SIGCOMM 2023 Conference
    Anomaly detection is an essential building block of many applications, including DDoS detection, root cause analysis, traffic estimation, and change detection. A vital part of detecting anomalies is establishing a sense of normality, e.g., by learning distributions for various features from benign traffic. Learning these distributions in the control plane requires coping with the limited visibility of sampling; learning distributions in the data plane requires relying on simplistic techniques because of hardware constraints. We propose a novel data- and control-plane co-design for learning distributions: in the control plane, we search for candidate distributions with Bayesian optimization; in the data plane, we evaluate how well each distribution matches _all observed_ traffic, without missing rare events. The aggregated evaluation results are fed back to the control plane to guide the optimization and learn accurate distributions. Our key insight is that while learning and optimization are infeasible in the data plane, evaluating distributions is feasible and leverages data plane strengths. We confirm the feasibility of our approach with a preliminary evaluation.
Publications 1 - 10 of 13