Udhaya Kumar Dayalan

ORCID: 0000-0002-7707-5364
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced MIMO Systems Optimization
  • Telecommunications and Broadcasting Technologies
  • IoT and Edge/Fog Computing
  • Image and Video Quality Assessment
  • Video Coding and Compression Technologies
  • Software-Defined Networks and 5G
  • Vehicular Ad Hoc Networks (VANETs)
  • Big Data and Business Intelligence
  • IoT Networks and Protocols
  • Advanced Wireless Communication Technologies
  • Multimedia Communication and Technology
  • Blockchain Technology Applications and Security
  • Cloud Computing and Resource Management
  • Caching and Content Delivery
  • Context-Aware Activity Recognition Systems
  • Wireless Networks and Protocols
  • Power Line Communications and Noise
  • Millimeter-Wave Propagation and Modeling
  • Opportunistic and Delay-Tolerant Networks
  • Cooperative Communication and Network Coding

University of Minnesota
2020-2024

Twin Cities Orthopedics
2021-2024

University of Minnesota System
2022

The emerging 5G services offer numerous new opportunities for networked applications. In this study, we seek to answer two key questions: i) is the throughput of mmWave predictable, and ii) can build "good" machine learning models prediction? To end, conduct a measurement study commercial in major U.S. city, focusing on as perceived by applications running user equipment (UE). Through extensive experiments statistical analysis, identify UE-side factors that affect performance quantify what...

10.1145/3419394.3423629 article EN 2020-10-23

Recent measurement studies show that commercial mmWave 5G can indeed offer ultra-high bandwidth (up to 2 Gbps), capable of supporting bandwidth-intensive applications such as ultra-HD (UHD) 4K/8K and volumetric video streaming on mobile devices. However, also exhibits highly variable throughput performance incurs frequent handoffs (e.g., between 4G), due its directional nature, signal blockage other environmental factors, especially when the device is mobile. All these issues make it...

10.1145/3472771.3474036 article EN 2021-08-18

We introduce Kaala, a scalable, hybrid, end-to-end IoT system simulator that can integrate with diverse, real-world cloud services. Many simulators run in isolation and do not interface systems or servers. This makes it difficult for experiments to fully replicate the diversity exists end-to-end, systems. Kaala is intended bridge gap between simulation real world. The interact services, such as those offered by Amazon, Microsoft Google. leverages vendor-provided software development kits...

10.1145/3538393.3544937 article EN 2022-08-11

5G offers a slew of new features and capabilities to support whole gamut applications. On the other hand, radio (NR), especially, high-band mmWave radio, also poses challenges, as shown by recent measurement studies commercial services. In order effectively classes application such extra low-latency and/or high-bandwidth applications, we argue that truly cross-layer network-application integration exposes semantics enable beyond (B5G) networks make intelligent decisions, e.g., for dynamic...

10.1145/3472727.3472798 article EN 2021-07-29

As the plethora of Internet Things (IoT) devices gradually make their way into our lives, several Cloud Service Providers (CSPs) have developed IoT gateway platforms (SDKs) that solely connects to respective cloud. Such gateways 1) cumbersome device configuration; 2) inflexible data managements; and 3) support no/little cross-vendor edge computation cloud analytics. We term these commercial SDKs as cloud-centric. In this paper, we study state-of-the-art vendor-locked Gateway solutions...

10.1109/ccgrid51090.2021.00083 article EN 2021-05-01

We exploit eBPF+XDP to scale and accelerate software packet processing in (O-RAN compliant) disaggregated 5G RAN (Radio Access Network). argue that the Central Unit User Plane (CU-UP) component is likely bottleneck user plane data path therefore focuses on optimizing its performance. propose an eBPF/XDP-based framework, PRAVEGA, discuss additional options for further improvements.

10.1145/3609021.3609303 article EN 2023-08-18

The IoT world is evolving with the latest technology trends, like edge computing, augmented & virtual reality, machine learning, robotics, and 5G. With digital transformation happening in Industry 4.0, many industries are moving toward private 5G networks. There massive number (hundreds to thousands) of devices a single factory depending on scale industry these factories consists critical devices, fire or gas sensors which need operate reliably less latency. To efficiently realize...

10.1109/mnet.002.2200498 article EN IEEE Network 2023-05-01

Numerous cloud service providers (CSPs) have developed IoT gateways and devices that connect solely to their respective clouds. We term these cloud-centric. In this paper, we propose an alternative, edge-centric approach developing gateways, Edge-Centric Gateways, or ECIoT. ECIoT will: enable sites direct sensor data the CSP of choice for processing storage permit be easily efficiently forwarded multiple CSPs simultaneously, which can simplify functions in multi-vendor systems. Evaluation a...

10.1145/3446382.3448667 article EN 2021-02-20

Unlike previous generation cellular technologies, 5G networks support diverse radio bands from low-band, mid-band to (mmWave) high-band, and offer a wide variety of new enhanced features. In particular, 3GPP standards adopt flow-based Quality-of-Service (QoS) framework that allows more flexibility in mapping QoS "flows" data bearers. Nonetheless, the classes are pre-defined treatment is limited "flow" level. As we will argue an earlier paper, cannot fully intelligently utilize diversity...

10.1109/dcoss54816.2022.00075 article EN 2022-05-01

Starting with 5G, radio access networks (RANs) are moving towards an disaggregated architecture, most of its functionality (except for the low-level PHY layer) implemented in software. While software affords benefits programmability and scale-out, it is also far slower than hardware. This further compounded by needs more complex, dynamic intelligent features Next-Generation (NextG) RANs. In this work, we advocate eBPF (extended Berkeley Packet Fil-ter)+XDP (eXpress Data Path) based framework...

10.1109/fnwf58287.2023.10520475 article EN 2023-11-13
Coming Soon ...