arXiv subjects

Aashish Gottipati

Publications and source records attributed to Aashish Gottipati.

6 recordsLinked to original sources

arXiv2026

Offline Meta-learning for Real-time Bandwidth Estimation

Real-time video applications require dynamic bitrate adjustments based on network capacity, necessitating accurate bandwidth estimation (BWE). We introduce Ivy, a novel BWE method that leverages offline meta-learning to combat data drift and maximize user Quality of Experience (QoE). Our approach dynamically selects the most suitable BWE algorithm for current network conditions, enabling effective adaptation to changing environments without requiring live network interactions. We implemented our method in Microsoft Teams and demonstrated that Ivy can enhance QoE by 5.9% to 11.2% over individual BWE algorithms and by 6.3% to 11.4% compared to existing online meta heuristics. Additionally, we show that our method is more data efficient compared to online meta-learning methods, achieving up to 21% improvement in QoE while requiring significantly less training data.

cs.NI↗

arXiv2025

Dynamic Pacing for Real-time Satellite Traffic

Google's congestion control (GCC) has become a cornerstone for real-time video and audio communication, yet its performance remains fragile in emerging Low Earth Orbit (LEO) networks. In this paper, we study the behavior of videoconferencing systems in LEO constellations. We observe that video quality degrades due to inherent delays and network instability introduced by the high altitude and rapid movement of LEO satellites, with these effects exacerbated by WebRTC's conventional "one-size-fits-all" sender-side pacing queue management. To address these challenges, we introduce a data-driven queue management mechanism that tunes the maximum pacing queue capacity based on predicted handover activity, minimizing latency during no-handover periods and prioritizing stability when entering periods of increased handover activity. Our method yields up to 3x improvements in video bitrate and reduces freeze rate by 62% in emulation, while delivering up to a 41% reduction in freeze rate and 40% decrease in mean packet loss on real Starlink constellations compared to WebRTC's default pacing queue policy.

cs.NI↗

arXiv2025

Congestion Control System Optimization with Large Language Models

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms continue to exhibit suboptimal performance across diverse network environments. In this paper, we introduce a novel approach that automatically optimizes congestion control algorithms using large language models (LLMs). Our framework consists of a structured algorithm generation process, an emulation-based evaluation pipeline covering a broad range of network conditions, and a statistically guided method to substantially reduce evaluation time. Empirical results from four distinct LLMs validate the effectiveness of our approach. We successfully identify algorithms that achieve up to 27% performance improvements over the original BBR algorithm in a production QUIC implementation. Our work demonstrates the potential of LLMs to accelerate the design of high-performance network algorithms and paves the way for broader applications in networking systems.

cs.NI↗

arXiv2025

FlexRDZ: Autonomous Mobility Management for Radio Dynamic Zones

FlexRDZ is an online, autonomous manager for radio dynamic zones (RDZ) that seeks to enable the safe operation of RDZs through real-time control of deployed test transmitters. FlexRDZ leverages Hierarchical Task Networks and digital twin modeling to plan and resolve RDZ violations in near real-time. We prototype FlexRDZ with GTPyhop and the Terrain Integrated Rough Earth Model (TIREM). We deploy and evaluate FlexRDZ within a simulated version of the Salt Lake City POWDER testbed, a potential urban RDZ environment. Our simulations show that FlexRDZ enables up to a 20 dBm reduction in mobile interference and a significant reduction in the total power of leaked transmissions while preserving the overall communication capabilities and uptime of test transmitters. To our knowledge, FlexRDZ is the first autonomous system for RDZ management.

cs.NI↗

arXiv2025

Offline to Online Learning for Real-Time Bandwidth Estimation

Real-time video applications require accurate bandwidth estimation (BWE) to maintain user experience across varying network conditions. However, increasing network heterogeneity challenges general-purpose BWE algorithms, necessitating solutions that adapt to end-user environments. While widely adopted, heuristic-based methods are difficult to individualize without extensive domain expertise. Conversely, online reinforcement learning (RL) offers ease of customization but neglects prior domain expertise and suffers from sample inefficiency. Thus, we present Merlin, an imitation learning-based solution that replaces the manual parameter tuning of heuristic-based methods with data-driven updates to streamline end-user personalization. Our key insight is that transforming heuristic-based BWE algorithms into neural networks facilitates data-driven personalization. Merlin utilizes Behavioral Cloning to efficiently learn from offline telemetry logs, capturing heuristic policies without live network interactions. The cloned policy can then be seamlessly tailored to end user network conditions through online finetuning. In real intercontinental videoconferencing calls, Merlin matches our heuristic's policy with no statistically significant differences in user quality of experience (QoE). Finetuning Merlin's control policy to end-user environments enables QoE improvements of up to 7.8% compared to the heuristic policy. Lastly, our IL-based design performs competitively with current state-of-the-art online RL techniques but converges with 80% fewer videoconferencing samples, facilitating practical end-user personalization.

cs.NI↗

arXiv2024

Designing Network Algorithms via Large Language Models

We introduce NADA, the first framework to autonomously design network algorithms by leveraging the generative capabilities of large language models (LLMs). Starting with an existing algorithm implementation, NADA enables LLMs to create a wide variety of alternative designs in the form of code blocks. It then efficiently identifies the top-performing designs through a series of filtering techniques, minimizing the need for full-scale evaluations and significantly reducing computational costs. Using adaptive bitrate (ABR) streaming as a case study, we demonstrate that NADA produces novel ABR algorithms -- previously unknown to human developers -- that consistently outperform the original algorithm in diverse network environments, including broadband, satellite, 4G, and 5G.

cs.NI↗