arXiv subjects

Sanjay Chandrasekaran

Publications and source records attributed to Sanjay Chandrasekaran.

6 recordsLinked to original sources

arXiv2026

NetReplica: A Programmable Substrate for Bottleneck-Centric Network Data Generation

The behavior of Internet applications is shaped by congestion dynamics at bottleneck links, yet data capturing application behavior across diverse bottleneck regimes remains scarce. Bridging this gap requires a data-generation substrate that simultaneously provides controllability, composability, fidelity, and replicability, capabilities that existing approaches struggle to achieve together. This paper introduces NetReplica, a programmable substrate for bottleneck-centric data generation guided by progressive disaggregation. NetReplica (i) decouples bottleneck intent from execution, (ii) separates static bottleneck attributes from dynamic congestion pressure, and (iii) disaggregates observed demand dynamics from their original trace context through Cross-Traffic Profiles (CTPs). CTPs transform passive packet traces into reusable, composable pressure signals that can be selected and transformed to specify dynamic bottleneck behavior. Our evaluation shows that NetReplica provides all four capabilities simultaneously and, in an ABR case study, generates datasets that remain realistic while expanding coverage of underrepresented regimes, improving the performance of trained models. In particular, NetReplica reduces transmission-time prediction error for the well-explored Fugu model by up to 47%. Together, these results demonstrate that NetReplica is a practical, fully programmable bottleneck-centric data-generation substrate for developing production-ready protocols, applications, and learning artifacts.

cs.NI↗

arXiv2026

A Gray-Box Approach for Decentralized Grid-Equivalent Model Identification

We propose a decentralized, frequency-domain identification algorithm that estimates the grid-equivalent model using local measurements from the perspective of each converter. Since local electric signals in a multi-converter setup are affected by voltage inputs from the grid, estimating a direct equivalent impedance yields biased and inaccurate results. To overcome this, we design a framework that decouples the effect of the equivalent impedance (passive) from that of the equivalent voltage (active). The parameters and equivalent grid voltages are then estimated using a least-squares algorithm and a Kalman filter, respectively, applied across frequency samples, with additional pre-processing techniques to remove the influence of the grid on the locally estimated models. We then demonstrate the accuracy and performance of our algorithm on an interconnected $5-$converter system in grid-forming mode, with minimal voltage excitations and non-nominal operating conditions.

eess.SP↗

arXiv2025

NetGent: Agent-Based Automation of Network Application Workflows

We present NetGent, an AI-agent framework for automating complex application workflows to generate realistic network traffic datasets. Developing generalizable ML models for networking requires data collection from network environments with traffic that results from a diverse set of real-world web applications. However, using existing browser automation tools that are diverse, repeatable, realistic, and efficient remains fragile and costly. NetGent addresses this challenge by allowing users to specify workflows as natural-language rules that define state-dependent actions. These abstract specifications are compiled into nondeterministic finite automata (NFAs), which a state synthesis component translates into reusable, executable code. This design enables deterministic replay, reduces redundant LLM calls through state caching, and adapts quickly when application interfaces change. In experiments, NetGent automated more than 50+ workflows spanning video-on-demand streaming, live video streaming, video conferencing, social media, and web scraping, producing realistic traffic traces while remaining robust to UI variability. By combining the flexibility of language-based agents with the reliability of compiled execution, NetGent provides a scalable foundation for generating the diverse, repeatable datasets needed to advance ML in networking.

cs.AI↗

arXiv2025

Reactive power flow optimization in AC drive systems

This paper explores a limit avoidance approach in the case of input (modulation) and output (current) constraints with the aim of enhancing system availability of AC drives. Drawing on the observation that, in a certain range of reactive power, there exists a trade-off between current and modulation magnitude, we exploit this freedom and define a constrained optimization problem. We propose two approaches, one in the form of an activation-function which drives the reactive power set-point towards safety, and an approach which uses online feedback optimization to set the reactive power dynamically. Both methods compromise reactive power tracking accuracy for increased system robustness. Through a high fidelity simulation, we compare the benefits of the two methods, highlighting their effectiveness in industrial applications.

eess.SY↗

arXiv2024

Network-aware Recommender System via Online Feedback Optimization

Personalized content on social platforms can exacerbate negative phenomena such as polarization, partly due to the feedback interactions between recommendations and the users. In this paper, we present a control-theoretic recommender system that explicitly accounts for this feedback loop to mitigate polarization. Our approach extends online feedback optimization - a control paradigm for steady-state optimization of dynamical systems - to develop a recommender system that trades off users engagement and polarization reduction, while relying solely on online click data. We establish theoretical guarantees for optimality and stability of the proposed design and validate its effectiveness via numerical experiments with a user population governed by Friedkin-Johnsen dynamics. Our results show these "network-aware" recommendations can significantly reduce polarization while maintaining high levels of user engagement.

eess.SY↗

arXiv2023

Distributed State Estimation for Linear Time-Varying Systems with Sensor Network Delays

Distributed sensor networks often include a multitude of sensors, each measuring parts of a process state space or observing the operations of a system. Communication of measurements between the sensor nodes and estimator(s) cannot realistically be considered delay-free due to communication errors and transmission latency in the channels. We propose a novel stability-based method that mitigates the influence of sensor network delays in distributed state estimation for linear time-varying systems. Our proposed algorithm efficiently selects a subset of sensors from the entire sensor nodes in the network based on the desired stability margins of the distributed Kalman filter estimates, after which, the state estimates are computed only using the measurements of the selected sensors. We provide comparisons between the estimation performance of our proposed algorithm and a greedy algorithm that exhaustively selects an optimal subset of nodes. We then apply our method to a simulative scenario for estimating the states of a linear time-varying system using a sensor network including 2000 sensor nodes. Simulation results demonstrate the performance efficiency of our algorithm and show that it closely follows the achieved performance by the optimal greedy search algorithm.

eess.SY↗