arXiv subjects

Ammar Tahir

Publications and source records attributed to Ammar Tahir.

4 recordsLinked to original sources

arXiv2026

Analyzing Interaction Between CCAs and Traffic Policers

We describe details of a formal framework to study the interaction between traffic policers, implemented using phantom queues or token buckets, and any arbitrary congestion control algorithm (CCA). This framework allows network providers to figure out configurations for their traffic policers (phantom queue size, safe rate thresholds, etc.). We also use this framework to describe why CCAs interact differently with a traffic policer compared to traffic shapers.

cs.NI↗

arXiv2023

Centralized Management of a Wifi Mesh for Autonomous Farms

Emerging autonomous farming techniques rely on smart devices such as multi-spectral cameras, collecting fine-grained data, and robots performing tasks such as de-weeding, berry-picking, etc. These techniques require a high throughput network, supporting 10s of Mbps per device at the scale of tens to hundreds of devices in a large farm. We conduct a survey across 12 agronomists to understand these networking requirements of farm workloads and perform extensive measurements of WiFi 6 performance in a farm to identify the challenges in meeting them. Our measurements reveal how network capacity is fundamentally limited in such a setting, with severe degradation in network performance due to crop canopy, and spotlight farm networks as an emerging new problem domain that can benefit from smarter network resource management decisions. To that end, we design Cornet, a network for supporting on-farm applications that comprises: (i) a multi-hop mesh of WiFi routers that uses a strategic combination of 2.4GHz and 5GHz bands as informed by our measurements, and (ii) a centralized traffic engineering (TE) system that uses a novel abstraction of resource units to reason about wireless network capacity and make TE decisions (schedule flows, assign flow rates, and select routes and channels). Our evaluation, using testbeds in a farm and trace-driven simulations, shows how Cornet achieves 1.4 $\times$ higher network utilization and better meets application demands, compared to standard wireless mesh strategies.

cs.NI↗

arXiv2023

FedSS: Federated Learning with Smart Selection of clients

Federated learning provides the ability to learn over heterogeneous user data in a distributed manner while preserving user privacy. However, its current client selection technique is a source of bias as it discriminates against slow clients. For starters, it selects clients that satisfy certain network and system-specific criteria, thus not selecting slow clients. Even when such clients are included in the training process, they either struggle with the training or are dropped altogether for being too slow. Our proposed idea looks to find a sweet spot between fast convergence and heterogeneity by looking at smart client selection and scheduling techniques.

cs.DC↗

arXiv2022

Controlling Congestion via In-Network Content Adaptation

Realizing that it is inherently difficult to precisely match the sending rates at the endhost with the available capacity on dynamic cellular links, we build a system, Octopus, that sends real-time data streams over cellular networks using an imprecise controller (that errs on the side of over-estimating network capacity), and then drops appropriate packets in the cellular network buffers to match the actual capacity. We design parameterized primitives for implementing the packet dropping logic, that the applications at the endhost can configure differently to express different content adaptation policies. Octopus transport encodes the app-specified parameters in packet header fields, which the routers parse to execute the desired dropping behavior. Our evaluation shows how real-time applications involving standard and volumetric videos can be designed to exploit Octopus, and achieve 1.5-50 times better performance than state-of-the-art schemes.

cs.NI↗