Show simple item record

dc.contributor.advisorAlizadeh, Mohammad
dc.contributor.authorNasr-Esfahany, Arash
dc.date.accessioned2022-06-15T13:14:34Z
dc.date.available2022-06-15T13:14:34Z
dc.date.issued2022-02
dc.date.submitted2022-03-04T20:59:47.422Z
dc.identifier.urihttps://hdl.handle.net/1721.1/143352
dc.description.abstractEvaluating the real-world performance of network protocols is challenging. Randomized control trials (RCT) are expensive and inaccessible to most researchers, while expert-designed simulators fail to capture complex behaviors in real networks. We present CausalSim, a data-driven simulator for network protocols that addresses this challenge. Learning network behavior from observational data is complicated due to the bias introduced by the protocols used during data collection. CausalSim uses traces from an initial RCT under a set of protocols to learn a causal network model, effectively removing the biases present in the data. Using this model, CausalSim can then simulate any protocol over the same traces (i.e., for counterfactual predictions). Key to CausalSim is the novel use of adversarial neural network training that exploits distributional invariances that are present due to the training data coming from an RCT. Our extensive evaluation of CausalSim on both real and synthetic datasets and two use cases, including more than nine months of real data from the Puffer video streaming system, shows that it provides accurate counterfactual predictions, reducing prediction error by 44% and 53% on average compared to expert-designed and standard supervised learning baselines.
dc.publisherMassachusetts Institute of Technology
dc.rightsIn Copyright - Educational Use Permitted
dc.rightsCopyright MIT
dc.rights.urihttp://rightsstatements.org/page/InC-EDU/1.0/
dc.titleCausalSim: Toward A Causal Data-Driven Simulator For Network Protocols
dc.typeThesis
dc.description.degreeS.M.
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.identifier.orcidhttps://orcid.org/0000-0002-4844-6875
mit.thesis.degreeMaster
thesis.degree.nameMaster of Science in Electrical Engineering and Computer Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record