Chenggang Li

Download PDF Version Here!

Education

Publication

  1. Predicting Node Failure in Cloud Service Systems, Qingwei Lin et al. FSE/ESEC 2018.

    In recent years, many traditional software systems have migrated to cloud computing platforms and are provided as online services. A cloud service system typically contains a large number of computing nodes. In reality, nodes may fail and affect service availability. In this paper, we propose a failure prediction technique, which can predict the failure-proneness of a node in a cloud service system based on historical data, before node failure actually happens. The ability to predict faulty nodes enables the allocation and migration of virtual machines to the healthy nodes, therefore improving service availability.

  2. Cross Platform UI Test Migration. In submission to ASE 2021

Experience

Awards

Research & Projects

Ongoing Projects

Cross Platform UI Test Migration (Ongoing, Co-author), 2020-2021
Novel approach for bidirectional transfer of usage-based tests across different mobile platforms, with no source code required on either platform.
Our approach takes as input the binaries of the app-under-test written for both iOS and Android, as well as the existing tests for one of these platforms, and automatically generates such tests for the corresponding app on the other platform.

Past Projects

Anomaly Detection and Log Analysis, Spring 2019
Worked as an research intern at Beijing Bizseer Technologies to develop Deep learning based Anomaly Detection and Log Analysis Algorithms to help major commercial banks in china find out Anomaly in daily data and uncover root cause from massive heterogeneous data and log reports of their complex softwares and critical IT infrastructure.

As enterprise IT systems growing larger in size, there has been increasing complexity, large amount of log data, and emerging failures of all kinds. The difficulty of ensuring efficient and reliable operation of systems has increased dramatically. Anomaly Detection has been widely used in monitoring
infrastructure, however using static filter in Anomaly Detection cause a lot of false positives to be reported and could not handle the case of off hours and holidays.

AutoExavator, 2018
AutoExavator is an R&D project in iRootech Technology Co., Ltd and SANY, which enables autonomous driving and construction for heavy equipment

Azure Capacity Management at Microsoft Research Asia, 2017-2018
Predict capacity days-to-exhaustion and Develop Buffer Capacity Management strategy to reserve the empty node/core buffer to fit the tenant upgrade needs.

Compute and Storage Node Fault Prediction for Cloud Platforms, 2017
Proactive downtime prediction: our node fault and hardware fault prediction service can proactively reduce VM downtime, through guiding new VM allocation and removing risky nodes from rotation. Validation result shows our prediction technology can add 10+% more node fault reduction on top of existing advanced allocation strategy. The top 1,000 nodes with disk failures we predicted causes 21K+ min VM downtime within a month.

BoneyCare
BoneyCare is designed to help people with speech disorders improve their confidence and speaking quality. The App records, transcribes and analyzes a users speech patterns, which speech pathologists can then use to improve and accelerate their diagnoses and treatment plans. This project is a collaboration between 2nd year computer science students from two Chinese universities and UC Berkeley.

LightItUp
LightItUp is a hackathon solution based on MITM(man-in-the-middle) attack that helps late-owl students gain access over their dorm electricity meter and bypass enforcement of dorm electricity off after 23:00.

Contact

School Email: chenggan#usc.edu
Personal Email: Execute below command to find out.
openssl enc -base64 -d <<< b3NjYXJ4dml0YUBnbWFpbC5jb20K