Chase Wu Research

Chase Wu
Professor, Computer Science




Storage-Aware Task Scheduling for Big Data Workflows

We investigate a task scheduling problem to map a Directed Acyclic Graph (DAG)-structured computing workflow, where each vertex represents a MapReduce job consisting of multiple parallel tasks and each directed edge represents the communication dependency between two jobs, to an underlying PC cluster consisting of multiple computing nodes interconnected by disparate network links. We optimize the workflow execution performance by avoiding the two levels of data movement.

Distributed Information Composition

We investigate a problem of composing distributed information in big data systems. We construct analytical cost models and formulate a generic Distributed Information Composition problem in Big Data Systems, DIC-BDS, to aggregate multiple distributed datasets using a composition operator of specific complexity to produce one final output. We rigorously prove this problem to be NP-Complete and design two heuristic algorithms as solutions.

An illustration of how information is composed in a big data system to form a tree, where the root of the tree represents the final output.

Censorship Resistance in Blockchain-based IoT

We propose blockchain-based decentralized IoT management systems for censorship resistance, which include a “diffusion” function to deliver all messages from sensors to all full nodes and an augmented consensus protocol to check data losses, replicate processing outcome, and facilitate opportunistic outcome delivery.

We also leverage public key aggregation to reduce communication complexity and signature verification. The experimental results from proof-of-concept implementation and deployment in a real distributed environment show the feasibility and effectiveness in achieving censorship resistance.