Unison: A Parallel-Efficient and User-Transparent Network Simulation Kernel
Discrete-event simulation (DES) is a prevalent tool for evaluating network designs. Although
DES offers full fidelity and generality, its slow performance limits its application. To speed up …
DES offers full fidelity and generality, its slow performance limits its application. To speed up …
Sketchpolymer: Estimate per-item tail quantile using one sketch
1Estimating the quantile of distribution, especially tail distribution, is an interesting topic in
data stream models, and has obtained extensive interest from many researchers. In this …
data stream models, and has obtained extensive interest from many researchers. In this …
Building a Graph-based Deep Learning network model from captured traffic traces
C Güemes-Palau, MF Galmés… - arXiv preprint arXiv …, 2023 - arxiv.org
Currently the state of the art network models are based or depend on Discrete Event
Simulation (DES). While DES is highly accurate, it is also computationally costly and …
Simulation (DES). While DES is highly accurate, it is also computationally costly and …
m3: Accurate Flow-Level Performance Estimation using Machine Learning
Data center network operators often need accurate estimates of aggregate network
performance. Unfortunately, existing methods for estimating aggregate network statistics are …
performance. Unfortunately, existing methods for estimating aggregate network statistics are …
MQL: ML-assisted queuing latency analysis for data center networks
Data center network (DCN) performance analysis is becoming increasingly critical due to the
growing data center scale and proliferation of latency-critical applications. Packetlevel …
growing data center scale and proliferation of latency-critical applications. Packetlevel …
Securing Public Clouds using Dynamic Communication Graphs
We leverage a novel telemetry source available in public clouds today: periodic summaries
of every flow that enters or leaves any VM. A key aspect is that such telemetry can be …
of every flow that enters or leaves any VM. A key aspect is that such telemetry can be …
Graph Neural Network-Based SLO-Aware Proactive Resource Autoscaling Framework for Microservices
Microservice is an architectural style widely adopted in various latency-sensitive cloud
applications. Similar to the monolith, autoscaling has attracted the attention of operators for …
applications. Similar to the monolith, autoscaling has attracted the attention of operators for …
Similarity-Based Fast Analysis of Data Center Networks
SY Narayana, E Shriver, K O'Neal, N Yildirim… - IEEE Design & …, 2023 - ieeexplore.ieee.org
Similarity-Based Fast Analysis of Data Center Networks Page 1 1 Similarity-Based Fast
Analysis of Data Center Networks Shruti Yadav Narayana1, Emily Shriver2, Kenneth O’Neal2 …
Analysis of Data Center Networks Shruti Yadav Narayana1, Emily Shriver2, Kenneth O’Neal2 …
SplitSim: Large-Scale Simulations for Evaluating Network Systems Research
H Li, P Balasubramanian, M Meiers, J Li… - arXiv preprint arXiv …, 2024 - arxiv.org
When physical testbeds are out of reach for evaluating a networked system, we frequently
turn to simulation. In today's datacenter networks, bottlenecks are rarely at the network …
turn to simulation. In today's datacenter networks, bottlenecks are rarely at the network …
Mitigating the Performance Impact of Network Failures in Public Clouds
Some faults in data center networks require hours to days to repair because they may need
reboots, re-imaging, or manual work by technicians. To reduce traffic impact, cloud …
reboots, re-imaging, or manual work by technicians. To reduce traffic impact, cloud …