Chuanhao Sun

Chuanhao Sun

School of Informatics

Research Associate at University of Edinburgh, NetSys & Institute for Computing Systems Architecture

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

articles

5G development: Automation and the role of artificial intelligence

Published in Wiley 5G Ref: The Essential 5G Reference, 2020

This survey paper explores the future evolution of 5G through the integration of AI, moving towards a fully automated and intelligent network generation. We provide a comprehensive review of current automation efforts in 5G research and highlight several promising directions for future advancements. Read more

GenDT: Mobile Network Drive Testing Made Efficient with Generative Modeling

Published in ACM CoNEXT'22 - Best Paper Shortlist, 2022

We leverage open-source contextual data as input conditions to generate city-scale radio coverage KPIs. GenDT accurately models the stochastic characteristics of radio signals, producing the expected distribution of user experiences. Additionally, GenDT incorporates an uncertainty-driven active learning mechanism to guide future field tests, significantly reducing measurement overhead while enhancing the efficiency of data collection. Read more

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

Published in ICML'24, 2024

Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from lowdimensional inputs, such as 3D view synthesis and time series regression with neural tangent kernels. Despite their effectiveness, existing PEs require manual, empirical adjustment of crucial hyperparameters, specifically the Fourier features, tailored to each unique task. Further, PEs face challenges in efficiently learning high-frequency functions, particularly in tasks with limited data. In this paper, we introduce sinusoidal PE (SPE), designed to efficiently learn adaptive frequency features closely aligned with the true underlying function. Our experiments demonstrate that SPE, without hyperparameter tuning, consistently achieves enhanced fidelity and faster training across various tasks, including 3D view synthesis, Text-toSpeech generation, and 1D regression. SPE is implemented as a direct replacement for existing PEs. Its plug-and-play nature lets numerous tasks easily adopt and benefit from SPE.. Read more

SpotLight: Accurate, Explainable and Efficient Anomaly Detection for Open RAN

Published in ACM MobiCom'24, 2024

The Open RAN architecture, with disaggregated and virtualized RAN functions communicating over standardized interfaces, promises a diversified and multi-vendor RAN ecosystem. However, these same features contribute to increased operational complexity, making it highly challenging to troubleshoot RAN related performance issues and failures. Tackling this challenge requires a dependable, explainable anomaly detection method that Open RAN is currently lacking. To address this problem, we introduce SpotLight, a tailored system archtecture with a distributed deep generative modeling based method running across the edge and cloud. SpotLight takes in a diverse, fine grained stream of metrics from the RAN and the platform, to continually detect and localize anomalies. It introduces a novel multi-stage generative model to detect potential anomalies at the edge using a lightweight algorithm, followed by anomaly confirmation and an explainability phase at the cloud, that helps identify the minimal set of KPIs that caused the anomaly. We evaluate SpotLight using the metrics collected from an enterprise-scale 5G Open RAN deployment in an indoor office building. Our results show that compared to a range of baseline methods, SpotLight yields significant gains in accuracy (13% higher F1 score), explainability (2.3 − 4× reduction in the number of reported KPIs) and efficiency (4 − 7× bandwidth reduction). Read more

NetGSR: Towards Efficient and Reliable Network Monitoring with Generative Super Resolution

Published in ACM CoNEXT'24, 2024

Network monitoring systems are a key building block in today’s networks. They all follow a common framework where measurement data from network elements is aggregated at a central collector for network-wide visibility. When designing network monitoring systems, two key properties have to be taken into account: (1) efficiency, to minimize the communication overhead from network elements to the collector; (2) high-fidelity, to faithfully represent the network status. However, in presence of network dynamics, tracking the right operating point to ensure both high fidelity and efficiency is hard and we observe that prior monitoring approaches trade off one for the other. In this paper, we show that it is possible to satisfy both these properties with NetGSR, a new deep learning based solution we introduce that reconstructs the fine-grained behavior of network status at the collector while requiring low resolution measurement data from network elements. This is achieved through a combination of a new custom-tailored conditional deep generative model (DistilGAN), and a new feedback mechanism (Xaminer) based on model uncertainty estimation and denoising that allows the collector to adjust the sampling rate for measurement data from network elements, at run-time. We extensively evaluate NetGSR using three different network scenarios with corresponding real-world network monitoring datasets as well as two downstream use cases. We show that NetGSR can faithfully reconstruct fine-grained network status with 25x greater measurement efficiency than prior approaches while requiring only few ms of inference time at the collector. Read more

talks

GenDT: Mobile Network Drive Testing Made Efficient with Generative Modeling

Published in ACM CoNEXT 2022, 2022

Drive testing continues to play a key role in mobile network optimization for operators but its high cost is a big concern. Alternative approaches like virtual drive testing (VDT) target device testing in the lab whereas MDT or crowdsourcing based approaches are limited by the incentives users have to participate and contribute measurements. With the aim of augmenting drive testing and significantly reducing its cost, we propose GenDT, a novel deep generative model that synthesizes high-fidelity time series of key radio network key performance indicators (KPIs)… Read more

Efficient Mobile Network Drive Testing with Deep Generative Modeling

Published in MobiUK 2023, 2023

The main goal of drive testing is to assess and optimize mobile network coverage, capacity, and quality of service (QoS) through measurement. This involves collecting field measurements in a controlled manner by driving or walking in a target scenario. Drive testing continues to play a key role in mobile network optimization for operators. The principal concern with traditional drive testing is that it requires manual effort to obtain measurements, making it costly and time-consuming. Several measurement tools are available to perform drive or walk testing… Read more

AppShot: A Conditional Deep Generative Model for Synthesizing Service-Level Mobile Traffic Snapshots at City Scale

Published in SCONE – the SCOttish Networking Event, 2023

Service-level mobile traffic data enables research studies and innovative applications with a potential to shape future service-oriented communication systems and beyond. However, real-world datasets reporting measurements at the individual service level are hard to come by due to privacy or industrial secrecy reasons. APPSHOT is a model for producing synthetic high-fidelity snapshots of the traffic generated by mobile services… Read more